Abstract
Driving intelligence tests are critical to the development and deployment of autonomous vehicles. The prevailing approach tests autonomous vehicles in life-like simulations of the naturalistic driving environment. However, due to the high dimensionality of the environment and the rareness of safety-critical events, hundreds of millions of miles would be required to demonstrate the safety performance of autonomous vehicles, which is severely inefficient. We discover that sparse but adversarial adjustments to the naturalistic driving environment, resulting in the naturalistic and adversarial driving environment, can significantly reduce the required test miles without loss of evaluation unbiasedness. By training the background vehicles to learn when to execute what adversarial maneuver, the proposed environment becomes an intelligent environment for driving intelligence testing. We demonstrate the effectiveness of the proposed environment in a highway-driving simulation. Comparing with the naturalistic driving environment, the proposed environment can accelerate the evaluation process by multiple orders of magnitude.
Highlights
Driving intelligence tests are critical to the development and deployment of autonomous vehicles
Human driving behaviors have been extensively investigated in the transportation engineering domain, most existing models were developed for traffic flow analysis purposes, which may not be suitable for driving safety assessment
The goal of naturalistic driving environment (NDE) is to generate stochastic human driving behaviors, whose probabilistic distributions are consistent with the naturalistic driving data (NDD)
Summary
Driving intelligence tests are critical to the development and deployment of autonomous vehicles. Most existing methods use the naturalistic driving environment (NDE) for driving intelligence testing of AVs. For example, on-road methods test AVs in the real-world NDE, while most simulation methods test high-fidelity AV models in life-like simulations of NDE, such as Intel’s CARLA6, Microsoft’s AirSim[7], NVIDIA’s Drive Constellation[8], Google/Waymo’s CarCraft[9], Baidu’s AADS10, etc. On-road methods test AVs in the real-world NDE, while most simulation methods test high-fidelity AV models in life-like simulations of NDE, such as Intel’s CARLA6, Microsoft’s AirSim[7], NVIDIA’s Drive Constellation[8], Google/Waymo’s CarCraft[9], Baidu’s AADS10, etc All these methods suffer from inefficiency issue, because of the “curse of dimensionality” and the rareness of events in NDE, as discussed above. Such a driving environment contains numerous distinctive spatiotemporal combinations of scenarios, which cannot be handled by existing scenario-based approaches
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
