Simulation Framework for Testing Autonomous Vehicles in a School for the Blind Campus

With the advent of increasing autonomous vehicles on public roads, the safety of vulnerable road users such as pedestrians, cyclists, etc. has never been more important. These especially include Blind or Visually Impaired (BVI) pedestrians who face difficulty in making confident decisions in road crossings without the help of accessible pedestrian signals (APS). This paper addresses some of the safety measures that can be taken to improve and assess the safety of BVI pedestrians in a controlled environment like a BVI school campus where autonomous vehicles are operated. The majority of research on autonomous vehicle safety does not consider the edge cases of encounters with BVI pedestrians. Based on this motivation, requirements and characteristics of Non-BVI and BVI pedestrians have been stated along with the motion models used to predict their future movements. Existing tools based on Bayesian multi-model filters were used for pedestrian tracking and motion predictions. These can be used for developing collision avoidance algorithms such as automatic emergency braking and evasive maneuvering. Path planning algorithms were developed and used to generate collision avoidance maneuvers. Extensive testing of the algorithms was carried out for multiple scenarios as defined by NHTSA’s pre-crash scenarios. For this purpose, a realistic virtual simulation environment was created using the CARLA Simulator. Other edge case scenarios such as distracted pedestrians, sensor latency, etc. were also tested using this simulation framework. The safety analysis assessment for the test scenarios was performed using pre-defined metrics.