Safe Trajectory Design
DESCRIPTION
Trajectory planning for autonomous vehicles requires a mathematical model to describe how the vehicle moves through the world. However, models are imperfect, and accounting for model uncertainty is critical to ensuring safety. Furthermore, depending on model complexity, a trajectory planner may or may not be able to find solutions in real time. The proposed work uses low-complexity models to produce trajectories, and bounds the model error of the vehicle's ability to follow such trajectories. The range of states a vehicle can achieve in this framework is computed offline in a Forward Reachable Set (FRS), which is represented as a function that conservatively approximates the vehicle's states (in 2-D space) and its parameterized trajectories. The FRS is intersected with obstacles in the world at runtime to exclude unsafe trajectories; optimization over the remaining trajectories ensures that a trajectory is chosen that is safe for the vehicle to follow despite uncertainty. This method is demonstrated in simulated comparison against the Rapidly-exploring Random Trees (RRT) and Nonlinear Model Predictive Control (NMPC) approaches; and on a Segway RMP mobile robot and a Rover carlike robot.
Related Publications
S. Vaskov, et al. "Towards Provably Not-at-Fault Control of Autonomous Robots in Arbitrary Dynamic Environments." arXiv preprint arXiv:1902.02851 (2019). [PDF]
S. Vaskov, et al. "Guaranteed Safe Reachability-based Trajectory Design for a High-Fidelity Model of an Autonomous Passenger Vehicle." arXiv preprint arXiv:1902.01786 (2019). [PDF]
S. Kousik, et al. "Bridging the gap between safety and real-time performance in receding-horizon trajectory design for mobile robots." arXiv preprint arXiv:1809.06746 (2018). [PDF] [Video]
S. Kousik, et al. "Safe trajectory synthesis for autonomous driving in unforeseen environments." ASME 2017 Dynamic Systems and Control Conference. American Society of Mechanical Engineers, 2017. [PDF]
@article{vaskov2019towards,
title={Towards Provably Not-at-Fault Control of Autonomous Robots in Arbitrary Dynamic Environments},
author={Vaskov, Sean and Kousik, Shreyas and Larson, Hannah and Bu, Fan and Ward, James and Worrall, Stewart and Johnson-Roberson, Matthew and Vasudevan, Ram},
journal={arXiv preprint arXiv:1902.02851},
year={2019}
}
@article{vaskov2019guaranteed,
title={Guaranteed Safe Reachability-based Trajectory Design for a High-Fidelity Model of an Autonomous Passenger Vehicle},
author={Vaskov, Sean and Sharma, Utkarsh and Kousik, Shreyas and Johnson-Roberson, Matthew and Vasudevan, Ramanarayan},
journal={arXiv preprint arXiv:1902.01786},
year={2019}
}
@article{kousik2018bridging,
title={Bridging the gap between safety and real-time performance in receding-horizon trajectory design for mobile robots},
author={Kousik, Shreyas and Vaskov, Sean and Bu, Fan and Johnson-Roberson, Matthew and Vasudevan, Ram},
journal={arXiv preprint arXiv:1809.06746},
year={2018}
}
@inproceedings{kousik2017safe,
title={Safe trajectory synthesis for autonomous driving in unforeseen environments},
author={Kousik, Shreyas and Vaskov, Sean and Johnson-Roberson, Matthew and Vasudevan, Ram},
booktitle={ASME 2017 Dynamic Systems and Control Conference},
pages={V001T44A005--V001T44A005},
year={2017},
organization={American Society of Mechanical Engineers}
}