This repository includes the source code associated with the paper "RACP: Risk-Aware Contingency Planning with Multi-Modal Predictions". The paper presents an approach that leverages Bayesian beliefs over the distribution of potential policies of other road users to construct a novel risk-aware probabilistic motion planning framework. In particular, we propose a novel contingency planner that outputs long-term contingent plans conditioned on multiple possible intents for other actors in the traffic scene. The Bayesian belief is incorporated into the optimization cost function to influence the behavior of the short-term plan based on the likelihood of other agents’ policies. Furthermore, a probabilistic risk metric is employed to fine-tune the balance between efficiency and robustness. The algorithm is designed to work seamlessly with the CommonRoad simulation environment and adopts the Frenet planner base code from this repository.
The software has been tested on the following setup:
Please note that it is recommended to create an isolated virtual environment where the required Python packages can be installed.
To run this code, please follow this set of instructions:
$ git clone https://github.com/KhMustafa/Risk-aware-contingency-planning-with-multi-modal-predictions.gitpip install -r requirements.txtTo run the contingency planner, execute the following command from the root directory
python planner/Frenet/frenet_planner.pyIf relevant, consider citing:
@ARTICLE{mustafa2024racp,
author={Mustafa, Khaled and Jarne Ornia, Daniel and Kober, Jens and Alonso-Mora, Javier},
journal={IEEE Transactions on Intelligent Vehicles},
title={RACP: Risk-Aware Contingency Planning with Multi-Modal Predictions},
year={2024},
keywords={Planning under uncertainty; risk-awareness; autonomous vehicles; contingency planning; multi-modality}