Baldini, Francesca (Honda Research Institute), Tariq, Faizan M. (Honda Research Institute USA, Inc.), Bae, Sangjae (Honda Research Institute, USA), Isele, David (University of Pennsylvania, Honda Research Institute USA)

Don’t Get Stuck: A Deadlock Recovery Approach

Scheduled for presentation during the Poster Session "Operation and navigation of automated vehicles" (FrAT16), Friday, September 27, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

When multiple agents share space, interactions can lead to deadlocks, where no agent can advance toward their goal. This paper addresses this challenge with a deadlock recovery strategy. In particular, the proposed algorithm integrates hybridA-⋆, STL, and MPPI controller – where hybrid-A⋆ generates are reference path, STL defines a goal (deadlock avoidance) and constraints (w.r.t. traffic rules), and MPPI refines the path and speed accordingly. This STL-MPPI framework ensures the system compliance and safety of the resulting maneuvers, indicating a strong potential for complex traffic scenarios (and rules) in practice. The validation studies are conducted in simulations and with real scaled cars, respectively, to showcase the effectiveness of the proposed algorithm.