Browse Topic: Robotics

Items (2,172)
In this research, the design of a digital twin system for a Robot-Assembled Workpiece Transfer Station (RAWTS) and virtual commissioning with it were detailed, aiming for debugging high-repeatability, high-precision robotic motions. The system employs a structured three-layer digital twin framework, Physical, Digital, and Information Fusion layers, interconnected via an OPC UA communication architecture to enable real-time virtual-physical data synchronization. The 6-axis industrial robot’s kinematic model is established using the D-H parameter method, and the translational end-effector’s kinematic relationships are configured with defined OPEN/CLOSE poses. A behavior-driven digital twin model is constructed within NX MCD, incorporating lightweight-processed 3D geometry from SolidWorks. Virtual commissioning involves PLC and robot program integration, OPC UA-based signal mapping, and kinematic path planning with reachability validation to avoid singularities and collisions. Key joint angles at critical path points are optimized, and virtual-physical integration debugging is performed, resulting in first-attempt success in physical operation. The study demonstrates that the NX MCD-based digital twin approach effectively validates control logic, optimizes robot trajectories, reduces on-site debugging time, and enhances operational precision and safety, offering a practical reference for digital twin applications in robotic systems.
Zang, YupingWang, YeFu, HudaiLi, WeiweiJiang, ZhiyuWang, Dayu
Extreme winter weather often leads to ice accretion on transmission lines. Manual removal is inefficient, costly, and poses safety risks. To address this issue, this paper presents the design of a de-icing robot to replace manual operations for transmission line de-icing. The main content focuses on the detailed structural design of the robot, including the mobile platform, de-icing mechanism, and adaptive adjustment module. Finite element simulations are conducted on key components to verify the structural rationality and the correctness of material selection. The proposed de-icing robot enhances the safety of the de-icing process, improves operational efficiency, and provides a valuable reference for transmission line de-icing methods, demonstrating significant practical value.
Chang, HaoZhen, ChenHan, FengmeiLi, Cheng
In response to the challenges of training and rehabilitation for patients with leg dysfunction, this research focuses on two core requirements: “bionic adaptation” and “safety assistance”. It introduces a novel exoskeleton leg rehabilitation robot designed to support diverse rehabilitation exercises for individuals with leg disabilities during therapy. The robot system consists of a lumbar support structure, thigh mechanical components, calf mechanical components, leg fixation straps, and foot mechanical structures, and achieves multi degree of freedom motion simulation through three main joints: hip joint, knee joint, and ankle joint. Each mechanical leg has three independent degrees of freedom, which can effectively simulate the natural movements of the human lower limb, such as flexion, extension, abduction, etc., during the gait cycle, thus meeting the functional needs of patients for different movement modes during rehabilitation training. On the basis of structural design, this study further utilizes multi-body dynamics simulation software ADAMS to conduct kinematic and dynamic analysis of the exoskeleton robot. By simulating the joint torque of the exoskeleton legs under ideal working conditions, the rationality and smoothness of the mechanism design are verified. The simulation results not only reflect the performance of the robot in typical rehabilitation actions, but also provide a theoretical basis and data support for the selection and parameter matching of key execution components (such as servo motors, reducers, etc.), laying an important foundation for the physical development and control strategy optimization of the robot system.
Mu, XiaoqiMa, ChaoLi, WeijiePu, ShuaiLiu, JiaqiWang, RuiyinZhang, Xiaodong
The six-degree-of-freedom Stewart platform, as a high-precision parallel robot, is widely used in fields such as aerospace and precision manufacturing. However, its complex structure and diverse sources of error (such as manufacturing errors, assembly errors, rod deformation, etc.) make it difficult to effectively control position and attitude errors. This article proposes a Stewart platform position and attitude error compensation method, relying on the improved particle swarm optimization algorithm. By establishing a position and attitude error model for the platform and optimizing the driving joint error using the IPSO optimization, the position and attitude error of the platform have been significantly reduced, providing a new solution for error compensation of high-precision parallel robots.
Zhu, MingWang, Baichao
The propeller-driven Bernoulli adsorption device (PBD) has both propulsion and adsorption functions, being suitable for dual-mode underwater robots. Currently, there have been studies on the adsorption performance of PBD on the flat surface. However, the surface morphology of underwater engineering structures is different, and PBD’s adsorption performance on irregular walls still remains unknown. In this letter, based on the potential application scenarios of underwater dual-mode robots, we established four types of irregular wall models to investigate PBD’s adsorption performance on irregular walls. Through CFD simulations and experiments, the adsorption state was analyzed, and the adsorption performance was quantitatively studied.
Liu, SiyueHua, ZhongYang, Canjun
Large-sized irregular castings are critical components extensively employed in large-scale equipment manufacturing. Due to their substantial dimensions and complex geometries, the assembly and docking processes between different components present significant challenges. To address the docking problem between large-scale irregular castings, this study proposes a casting docking method based on relative pose, along with a modeling approach for irregular castings, and accomplishes the docking process through the control of an industrial robot. Firstly, the current poses of feature points on the docking surfaces are measured. Based on these measurements, the relative pose transformation relationship between the center point of the docking surface and the robot’s Tool Center Point (TCP) is established, thereby constructing the docking model. This model calculates the relative deviation between the current pose and the theoretical pose. Subsequently, the robot motion is controlled according to this deviation to achieve precise docking. Finally, a simulation environment was built using KUKA. Sim Pro with Office Lite to simulate the docking process of large-sized irregular castings. The results demonstrate that the relative pose-based docking method effectively accomplishes the docking task. This study provides an effective solution for the docking of large-sized irregular castings.
Liu, HaoranJia, HailiWang, AiminXigang, FanPeidong, Su
To address the high failure rate of rollers in coal mine belt conveyors, the inefficiency of manual replacement, and the operational disruptions caused by maintenance shutdowns, this study proposes a robotic arm system capable of replacing rollers without halting conveyor operations. The research focuses on the kinematic performance and path planning strategy of the robotic arm. A kinematic model is established using the Denavit–Hartenberg (DH) parameters, and the workspace distribution is analyzed via the Monte Carlo method. The results show that the horizontal reach exceeds 2020 mm and the vertical reach extends up to 2000 mm, which fully satisfies the spatial requirements for roller replacement across the entire conveyor system. In the path planning phase, an obstacle expansion model is constructed, and an improved Informed RRT* algorithm is implemented to generate collision-free trajectories, ensuring effective obstacle avoidance. To improve trajectory smoothness, path pruning and cubic B-spline interpolation are applied to refine the initial paths. For trajectory planning in joint space, quintic polynomial interpolation is employed, with boundary conditions set to ensure zero velocity and zero acceleration at both the start and end points, thereby guaranteeing smooth and stable motion of the robotic arm. Simulation results indicate that joint angles, angular velocities, and angular accelerations vary smoothly throughout the roller grasping process, without abrupt changes, and converge to zero at the beginning and end of the trajectory. End-effector trajectory tracking error analysis reveals positioning errors within 0.8 mm for side rollers and 3 mm for central rollers, well within acceptable engineering accuracy thresholds. This work provides a theoretical foundation and a practical implementation framework for advancing automation and intelligent operation in roller replacement tasks within coal mine belt conveyor systems.
Pu, CongyuanQian, Ke
Recent advances in precision motion technology have heightened the requirement for precise stiffness analysis in flexible mechanisms. This paper begins with a theoretical analysis, constructing a mathematical expression for the stiffness of flexible mechanisms, providing a systematic framework for analysis. Subsequently, the study employed finite element analysis on both single and double parallelogram flexible mechanisms to validate the proposed theoretical stiffness formulas. This process not only confirmed the effectiveness of the proposed expressions but also highlighted the influence of different structures on stiffness characteristics. The finite element analysis results validate the proposed theoretical model as an effective and reliable tool for predicting the stiffness of flexible mechanisms. By establishing a reliable predictive model, this research paves the way for the informed design and systematic optimization of next-generation flexible mechanisms in precision motion engineering.
Cai, Dongchen
Due to the inherent characteristics of large dimensions, complex curved surfaces, and densely distributed protrusions present in aerospace products, conventional offline programming and trajectory planning techniques for robots primarily prioritize the facilitation of uninterrupted grinding processes and the generation of points along trajectories on surfaces characterized by smoothness. However, these methods encounter challenges in identifying and proactively avoiding surface protrusions during the planning phase. The present paper puts forth a proposal for an automated robot trajectory planning method for grinding operations. This method is predicated on the integration of region partitioning and deformation correction. Specifically, this method first identifies protrusions based on curvature features and rule matching, followed by an analysis of the feasible workspace of a six-axis industrial robot equipped with an external axis. The product surface is discretized into multiple regional units according to the distribution characteristics of protrusions and the constraints of the feasible workspace. Subsequently, a parameter-optimized parallel sectioning method is employed to independently plan trajectories for each unit. The utilization of on-site measured point cloud data facilitates the analysis of contour deviations. In addition, grinding trajectories are dynamically corrected to meet high-precision process requirements. This approach effectively overcomes the challenge that trajectory planning for large-scale, complex-shaped products is easily affected by protrusions. According to the established methodology, the development of an offline programming software system for robotic automatic grinding was initiated. To this end, experiments were conducted on aircraft wall panels to plan and modify grinding trajectories using the proposed method. This process was undertaken to validate the effectiveness and engineering practicability of the proposed method.
Fan, ChanghaoWang, MingyangLv, RuiqiangZhou, Peng
To precisely simulate the nonlinear dynamic characteristics of a robotic arm grasping cylindrical objects from storage units, this study establishes a dynamic model of the robotic grasping process incorporating Coulomb and viscous friction models to characterize frictional properties. Furthermore, to effectively identify unknown parameters in the dynamic model, a parameter identification method based on the Superb Fairy-wren Optimization Algorithm (SFOA) is proposed. The root-mean-square error (RMSE) between the displacement responses from the dynamic model and the experimentally acquired displacement data serves as the optimization objective. Multiple sets of experimental data are utilized to identify the unknown parameters of the dynamic model. The results demonstrate that when the identified parameters are applied to the dynamic model, the goodness-of-fit between the model’s response displacement data and the experimental displacement data exceeds 0.999. This validates the effectiveness and accuracy of the proposed method for identifying unknown parameters in dynamic models.
Shen, ShaofengYang, LiuWang, ZihanHan, Qunyi
Pneumatic soft actuators are widely used in soft robotic systems because of their inherent compliance and smooth deformation. However, their practical application is often limited by low structural stiffness, restricted load-bearing capability, and insufficient tip output force. These limitations become more pronounced in tasks that require stable force transmission or precise interaction with the environment. In response to these limitations, this study proposes a stiffness-enhanced pneumatic soft actuator based on a modified multilayer structural configuration. The actuator integrates chamber layers, a constraint layer, and periodically distributed rigid reinforcement elements. This structural arrangement improves the way internal pressure is converted into bending deformation and external force output, while avoiding excessive local expansion of the chambers. Based on this actuator, a coupled theoretical model is developed to describe the relationship between internal pressure, bending angle, and tip force. The model considers both the hyperelastic behavior of the silicone material and the geometric constraints introduced by chamber deformation. Finite element simulations are performed to examine the actuator’s mechanical response under different pressure inputs. This effect becomes evident at higher pressure levels. Both free-bending behavior and tip contact force generation are analyzed. The simulation results follow the same trends as the theoretical predictions, and the overall deviation remains below 10% across the investigated pressure range. The agreement shows that the model reflects the main mechanical response. Compared with a conventional pneumatic soft actuator, the proposed design achieves higher stiffness and larger tip output force, while maintaining compliant motion and smooth bending behavior. The actuator structure and model may serve as a useful basis for pneumatic actuator design in force-demanding tasks.
Zhou, WenjingMa, RuiLu, MingyueWu, Yanyan
To obtain additional space for industrial sorting and assembly line labeling operations, this study conducts an analysis of the four-bar mechanism. Based on this analysis and combination, the redundant parallel mechanism is introduced. That is, on the basis of the traditional parallel mechanism with central rotation, the objective of expanding the working space is achieved. The degree of freedom of the screw theory and the disparities between the working space of this mechanism and that of the traditional mechanism are analyzed. Finally, through application analysis, it is demonstrated that the working space of this mechanism is variable and that the mechanism can adapt to diverse workplaces.
Li, WenqianZhang, Xiaojie
To address the challenges faced by micro flapping-wing flying robots in visual navigation—specifically, the large volume of visual information and the difficulty in transforming it into usable intelligent visual data—this paper proposes a clustering-based data-driven approach for directional and image perception. The aim is to enable intelligent visual navigation for flapping-wing robots. The proposed method performs clustering analysis on gyroscope data from the flapping-wing robot to extract directional features. Simultaneously, it applies clustering techniques to visual images captured by the robot to identify intelligent features such as edges. This approach enables the robot to acquire multiple optimized perceptual data types, thereby enhancing the behavior control system. Through the use of clustering analysis, the method not only improves the effectiveness of visual navigation but also extracts features related to visual targets and environmental information, providing technical support for visual target tracking. The experimental platform consists of a flapping-wing robot equipped with an onboard camera, and the proposed clustering-driven visual image perception approach has been experimentally validated. Experimental results demonstrate the high feasibility and effectiveness of the method in practical applications. The main contributions of this study lie in two aspects: (1) a clustering-driven visual image perception method for flapping-wing robots, and (2) a clustering-based approach for identifying posture and behavioral patterns of flapping-wing flying robots.
Li, ZixuanDing, WeiZhang, FengSong, MinLiu, ZhaomingMiao, LeiLiu, HaotianBai, NingTian, ShenCui, LongWang, Hongwei
Humanoid robots have long been the focus of science fiction, but today they are making their way into industrial environments thanks to the simultaneous maturing and convergence of multiple systems. Technology advances have driven the development of humanoid robots that have a wide range of movement and can perform demanding jobs around the clock without tiring. While currently representing a small share of all industrial robot deployments, the humanoid robot market is projected to grow rapidly over the next few years. In fact, estimates suggest the market could reach over $4 billion by 2030. This growth is being driven by factors such as labor shortages, falling costs, and the need for more flexible automation.
Spinoff is NASA’s annual publication featuring successfully commercialized NASA technology. This commercialization has contributed to the development of products and services in the fields of health and medicine, consumer goods, transportation, public safety, computer technology, and environmental resources.
Physical AI refers to applications in which AI technologies are connected to hardware that sense and execute actions in the physical world, allowing systems to autonomously act and adapt in real time. It spans automotive, robotics, industrial automation, smart infrastructure, aerospace, healthcare devices, software-defined machines, and more. Regardless of application, they have one thing in common: they must operate safely, reliably, and predictably in real world environments. Unlike purely digital AI, these systems are constrained by embedded electronics, timing, power, safety, and system-level interactions that are difficult to validate early.
Robotic manipulation remains one of the harder unsolved problems in automation engineering. Vision-based systems have matured considerably — object localization, pose estimation, and grasp planning from RGB-D data are now reliable enough for structured industrial environments. What vision cannot provide is contact information: whether a grasp is stable, whether a surface is beginning to slip, or how force is distributed across a fingertip during a hold. These signals are what close the control loop during manipulation, and without them, systems compensate through excessive grip force, conservative motion profiles, and large training datasets designed to paper over sensing uncertainty.
Humanoid robots are moving beyond hype-driven prototypes toward early commercial deployment, with automotive manufacturing emerging as the first scalable adoption market, according to IDTechX’s recent report Humanoid Robots 2026-2036: Technologies, Markets, and Opportunities.
Traditional industrial robotics has been built on traditional premises: define the task precisely, program the motion, and repeat it with minimal variation. This model has delivered reliability, speed, and scale across multiple application domains.
There's a well-known video from San Francisco in 1906 that comes up repeatedly in mobility discussions here in the 21st Century. If you haven't seen A Trip Down Market Street, it depicts the absolute bonkers variety of transportation methods used on Market Street back then: cable cars, horsecars, streetcars, pedestrians, automobiles and more. Past is prologue in a world that is adding scooters, delivery robots and other last-minute delivery vehicles to our streets. At the 2026 New York International Auto Show in April, Honda displayed its latest option in the form of the Fastport eQuad Prototype. The eQuad was originally unveiled at Eurobike 2025 and technically comes from Fastport, a micromobility venture from the Honda New Business Innovation Lab that was established to work on projects with global logistics companies. Jamie Davies, chief of operations for Fastport, called the group a kind of startup within Honda. “Three years ago,” Davies told SAE Media in New York, “a small group of Honda associates [came] together and [said], Okay, how can we create a new value for the company, a new business vertical? And so we've run the project in an agile way, working with customers all along the way to understand what their needs are, what the requirements are, and to bring to market something that fits.”
Blanco, Sebastian
Under a microscope, a bouquet of lollipop-like structures, each smaller than a grain of sand, waves gently in a petri dish of liquid. Suddenly, they snap together, like the jaws of a Venus flytrap, as a scientist waves a small magnet over the dish. What was previously an assemblage of tiny passive structures has transformed instantly into an active robotic gripper.
The future of Moon exploration may be rolling around a non-descript office on the CU Boulder campus. Here, a robot about as wide as a large pizza scoots forward on three wheels. It uses an arm with a claw at one end to pick up a plastic block from the floor, then set it back down.
Through a technology partnership that breaks new ground in the machine tool industry, Siemens offers an automation solution for the busy, multi-tasking, small to mid-sized machine shop, as it combines a digital twin of the software and programming of its popular SINUMERIK 828 CNC, working in tandem with a KUKA robot, to simplify the operation and programming in part handling for the machine tool operator.
ABB Robotics is integrating NVIDIA Omniverse libraries into ABB Robotics’ RobotStudio ® to help manufacturers deploy physical AI in real-world robotics applications.
Friendly robots, the ones people love to love, are quirky: R2-D2, C-3PO, WALL-E, BB-8, Marvin, Roz and Baymax. They’re emotional, prone to panic or bossy, empathetic and able to communicate like humans do — even when they communicate in only beeps and bloops.
Snake-like robots represent the future of rescue. Their slender bodies allow them to navigate narrow spaces, uneven terrain, and water surfaces, entering places that would be hazardous for humans. This could potentially save lives in earthquake-prone areas, like Japan.
While many manufacturers are enjoying demand for their products and have innovations in the pipeline, their growth strategy can sometimes stall. The issue might be due to workforce shortages, which can evolve from temporary setbacks to long-term challenges. For a variety of industries, helping hands are often hard to find, and it’s an issue that’s been consistent in recent years. Given this, many companies are considering transitioning to automation, including through the use of collaborative robots or cobots, for short.
Researchers in Carnegie Mellon University’s Robotics Institute (RI) have designed a system that makes an off-the-shelf quadruped robot nimble enough to walk a narrow balance beam.
Smart implants that not only stabilize a fracture but also monitor the healing process from day one — and deliver targeted support when required — are currently being developed at Saarland University by a team of engineers, medical researchers, and computer scientists. The engineering team led by Paul Motzki is contributing shape-memory micro-actuators with integrated sensing capabilities, while Bergita Ganse and her research group provide the medical expertise in fracture healing.
Picture a futuristic swarm of robots deployed on a time-sensitive task, like cleaning up an oil spill or assembling a machine. At first, adding robots is advantageous, since many hands make light work. But a tipping point comes when too many crowd the space, getting in each other’s way and slowing the whole task down.
Medical imaging technology is advancing rapidly, bringing new opportunities and challenges for machine designers. Systems that once required dedicated hospital rooms and significant floor space are becoming more compact, faster, mobile and capable of delivering increasingly detailed clinical insight. From advanced CT scanners to imaging platforms integrated with surgical robotics, imaging equipment is evolving toward more point-of-care (POC) solutions to meet rising expectations for diagnostic accuracy, procedural guidance and operational efficiency.
Robotic ultrasound scanning technology is a research hotspot in the field of medical imaging, and can achieve standardized and high-precision data acquisition. However, large force tracking errors occur during scanning, especially in complex human tissues, which can severely degrade image quality and diagnostic accuracy. Therefore, we propose an adaptive speed-regulated impedance control strategy to address this challenge, which innovatively combines the spline real-time interpolation and impedance control for constant force tracking. Firstly, the discrete ultrasound scanning paths are fitted to generate a smooth and synchronized interpolation trajectory. Then, the speed of the reference trajectory is adjusted in real time based on the Taylor formula to reduce the force tracking error. Experimental verification was conducted, and the results showed that the force tracking error increases with the increase of trajectory speed. In addition, at high speeds (e.g., 10 mm/s), the mean/variance of the force tracking error of the proposed method (0.3067N/0.2784) is reduced by 31.1%/37.4% respectively compared with the mean/variance of the traditional impedance control (0.4452N/0.4448), fully demonstrating the effectiveness of the proposed control strategy.
Min, KangZhang, LeShi, YudongFang, JinMo, HangjieLi, Xiaojian
Robot Arm Tracking Control refers to the control of robot end effectors following a prescribed trajectory as their movement in robotic systems. The work presents a combination of Kalman Filter Based Dynamic System Tracking with Reinforcement Learning Based Trajectory Planning. These two aspects of tracking and planning help the robotic manipulator dynamically track a target that is located on an arbitrary moving path. In particular, by using Kalman filtering to estimate the position of a moving target and to compensate for sensor noise and sparse sampling, we take high-precision estimation values of each point’s coordinates along the target trajectory as a reliable basis to build a policy network using reinforcement learning. Based on it, the robot manipulator could produce effective motion planning under its own dynamic capabilities and physical constraint limit. Comprehensive simulation results illustrate advantages of the new algorithm against the classical control method, confirm that the novel technique achieves better performance both in accuracy and computation efficiency. Also, this mixed control system can deal with complex moving path for track target object. Even when meet different obstacle and not sure measurement, it still works well with other moving obstacle in many conditions. This can be strong to face other dynamic obstacle even if have different situation with changing obstacle and uncertain data. It shows that this paper works as an attempt toward optimal solution to combine the model-based technique together with data-driven approach aiming to support real-time, highly accurate, adaptive prediction is based control technique, promising applications into industry and promoting more improved works related.
Yu, JingzeWang, YujiaLi, JunshenChen, CongXu, Peng
Soft robot systems demonstrate exceptional load-bearing capacity and spatial compliance during operation, with transformative potential in disaster response scenarios requiring adaptive morphology and hazardous material manipulation. By integrating the complementary advantages of soft robotics and particle jamming mechanisms, this study proposes a real-time variable-stiffness soft actuator, while systematically investigating its mathematical modeling framework and stiffness modulation principles. A deformation model for the variable stiffness soft actuator is established, followed by static analysis of the variable-stiffness members using particle jamming theory, with theoretical investigation of their stress distributions. Subsequently, a variable-stiffness driver was fabricated via additive manufacturing (3D printing), resulting in a flexible mechanical digit capable of stiffness tuning, A soft mechanical hand grasping test platform was built, and grasping experiments of objects of different shapes and sizes were conducted. Experimental validation confirms the influence of actuator dimensions, particle characteristics, and granule size distribution on both stress states and bending angles at the soft robotic digit’s distal segment. The obtained results establish theoretical foundations and advance variable-stiffness soft robotics research and associated stiffness regulation methodologies.
Wang, JianYuan, HaiyangDeng, HaishunChen, Jiaxian
The global automotive industry has reached a new era. If 2025 was defined by the cautious exploration of “experimental pilots” and the collection of vast data lakes from connected vehicle fleets, 2026 marks the year that data finally gains a mind of its own within the assembly plant. We are witnessing a transition from passive automation to integrated, agentic autonomy. This is a shift that moves beyond simple programmed robotic arms and toward systems capable of independent reasoning and real-time optimization. This evolution is not just a technical upgrade; it is a fundamental restructuring of how vehicles are built, de-risked, and scaled in an increasingly volatile global economy.
Panigrahi, Dijam
Scientists are striving to discover new semiconductor materials that could boost the efficiency of solar cells and other electronics. But the pace of innovation is bottlenecked by the speed at which researchers can manually measure important material properties.
In dynamic, unstructured environments like ship decks and even home kitchens, robots today still struggle to perform precision tasks such as tightening bolts or handling wires. This makes critical ship maintenance tasks difficult.
Is there a way to stick hard and soft materials together without any tape, glue, or epoxy? A new study published in ACS Central Science shows that applying a small voltage to certain objects forms chemical bonds that securely link the objects together. Reversing the direction of electron flow easily separates the two materials. This electroadhesion effect could help create biohybrid robots, improve biomedical implants, and enable new battery technologies.
A bird banking in a crosswind doesn’t rely on spinning blades. Its wings flex, twist and respond instantly to its environment.
USC Viterbi researcher received Office of Naval Research's Young Investigator Program award with Study on dexterous robotics. University of Southern California, Los Angeles, CA In dynamic, unstructured environments like ship decks and even home kitchens, robots today still struggle to perform precision tasks such as tightening bolts or handling wires. This makes critical ship maintenance tasks difficult. USC researcher, Erdem Bıyık, aims to advance robots' finger manipulation and integrate human feedback to enable real-time learning for robots in an upcoming three-year, $750,000 project funded by the Office of Naval Research (ONR).
Machina Labs recently closed its latest round of financing with $124 million, enough to develop a facility featuring up to 50 of its RoboCraftsman cells capable of producing thousands of complex structural assemblies for aerospace and defense customers - a list that already includes Lockheed Martin and the U.S. Air Force, among others. Founded in 2019, Machina Labs is a California-based company that seeks to reinvent metal manufacturing with a robot that uses artificial intelligence (AI) to rapidly form and assemble complex military grade structures directly from digital design files. RoboCraftsman is the company's manufacturing robot that leverages its proprietary “RoboForming” process to integrate multiple manufacturing processes - including metal forming, trimming, scanning, and heat treating - into a single containerized machine.
Autonomous mobile robots are becoming a key part of everyday operations in industries like manufacturing, logistics, healthcare, and even home assistance. A core requirement for these robots is the ability to navigate efficiently and reliably within their operating environments. To do this automation, the robot needs to understand its surroundings, figure out where it is on a map, and find a safe path from where it is to where it needs to go without bumping into anything. This paper presents an effective grid-based path planning solution for autonomous indoor navigation with a mobile robot. Achieving reliable and collision-free navigation in changing environments is a major challenge for mobile robotics. This is especially true when obstacles can appear unexpectedly, requiring quick re-planning. To tackle this issue, an improved A* algorithm was implemented to work closely with LiDAR for environmental awareness. The improved algorithm was added to the robot’s navigation system, and LiDAR data were used for simultaneous localization and mapping (SLAM) with Gmapping. A key improvement was integrating with ROS move_base control instead of using direct velocity control, enabling smoother motion and better path tracking. Additionally, the improved A* path is further simplified into a series of crucial waypoints, which are followed by move_base while the system watches LiDAR data in real time to spot obstacles. When a moving obstacle is detected, the planner recalculates the path and updates waypoints, enabling the robot to go around the obstruction and continue toward its goal safely. Tests in real indoor environments showed that the proposed system performs reliably at avoiding dynamic obstacles, navigating smoothly, and achieving goals. By combining heuristic planning, LiDAR perception, and ROS navigation tools, the proposed system offers a practical solution for autonomous mobile robot navigation.
Devaraj, Sriram SanjeevPark, Jungme
Formation control simplifies minimizing multi-robot cost functions by encoding a cost function as a shape the robots maintain. However, by reducing complex cost functions to formations, discrepancies arise between maintaining the shape and minimizing the original cost function. For example, a Diamond or Box formation shape is often used for protecting all members of the formation. When more information about the surrounding environment becomes available, a static shape often no longer minimizes the original protection cost. We propose a formation planner to reduce mismatch between a formation and the cost function while still leveraging efficient formation controllers. Our formation planner is a two-step optimization problem that identifies desired relative robot positions. We first solve a constrained problem to estimate non-linear and non-differentiable costs with a weighted sum of surrogate cost functions. We theoretically analyze this problem and identify situations where weights do not need to be updated. The weighted, surrogate cost function is then minimized using relative positions between robots. The desired relative positions are realized using a non-cooperative formation controller derived from Lyapunov’s direct approach. We then demonstrate the efficacy of this approach for military-like costs such as protection and obstacle avoidance. In simulations, we show a formation planner can reduce a single cost by over 75%. When minimizing a variety of cost functions simultaneously, using a formation planner with adaptive weights can reduce the cost by 40-60% . Formation planning provides better performance by minimizing a surrogate cost function that closely approximates the original cost function instead of relying on a shape abstraction.
Cornwall, ChazBos, Jeremy
As the adoption of electric vehicles continues to accelerate, the demand for their development and testing using chassis dynamometers has also increased significantly. Compared with internal combustion engine vehicles, chassis dynamometer testing for electric vehicles typically requires test durations several to several dozen times longer, resulting in substantially increased labor requirements. In addition, low-temperature testing is often required, further intensifying the workload associated with vehicle testing. To address these challenges, this study developed and evaluated a pedal robot designed to enable unmanned and automated testing. The pedal robot developed in this study weighs only 12 kg and can be installed within a few minutes. It is, to the authors’ knowledge, the world’s first pedal robot that mimics human driving behavior by using a single foot to operate both the accelerator and brake pedals. Unlike conventional driving robots, the actuators of the proposed system do not require direct mechanical attachment to the vehicle pedals, allowing for rapid installation. Furthermore, the robot is mounted on the driver-side floor, eliminating the need for attachment to the seat structure. The pedal robot features three degrees of freedom driven by three motors and employs artificial intelligence to recognize the shape and position of pedals across different vehicle models, thereby enabling automated test initiation without manual adjustment. The performance of the pedal robot was evaluated under UDDS, HWFET, and WLTC driving modes, and the results were analyzed in accordance with the SAE J2951 standard. Comparative evaluations demonstrated that the pedal robot achieved superior speed-tracking performance relative to that of an experienced human test driver. The developed pedal robot is currently being utilized for vehicle certification testing of electric and other vehicles at the Mobile Environment Research Center of the National Institute of Environmental Research in Korea. This paper presents a detailed analysis of the corresponding experimental results.
Lee, DaeyupKang, Ji MyeongJo, YechanChoi, SeongUnShin, JaesikKim, JongminKang, Keonwoo
Topology optimization (TO) of dynamic structures has traditionally been constrained to single-body components and simplified harmonic load assumptions. Extending TO to multibody dynamic systems (MBS) remains challenging due to complex coupling between inertia, mass distribution, and joint constraints. This paper presents an inertia-aware topology optimization framework that integrates mass moment of inertia (MMI) constraints within an enhanced Equivalent Static Displacement (ESD) methodology. Building upon the authors’ previously developed ESD framework, the proposed approach — termed Inertia-Augmented Equivalent Static Displacement (IA-ESD) — explicitly incorporates inertial effects arising from accelerations and joint interactions. The approach enables dynamically consistent optimization by coupling design-dependent inertia tensors with equivalent static displacements derived from nonlinear multibody dynamics. Case studies involving an MBB beam and a piston–connecting rod assembly demonstrate that accounting for MMI constraints yields lighter, stiffer, and dynamically balanced multibody topologies. The proposed method establishes a foundation for inertia-aware structural design with applications in aerospace, automotive, and robotics engineering.
Gupta, AakashTovar, Andres
Being an astronaut isn’t always glamorous.
Robots that can move through sand face significant challenges like dealing with higher forces than robots that move in air or water. They also get damaged more easily. However, the potential benefits of solving locomotion in sand include inspection of grain silos, measurements for soil contaminants, seafloor digging, extraterrestrial exploration, and search and rescue.
Items per page:
1 – 50 of 2172