Ensuring the safety of autonomous vehicles is a challenging task, especially if the planned trajectories do not consider all traffic rules or they are physically infeasible. Since replanning the complete trajectory is often computationally expensive, efficient methods are necessary for resolving such situations. One solution is to deform or repair an initiallyplanned trajectory, which we call trajectory repairing. Our approach first detects the part of an invalid trajectory that can stay unchanged. Afterward, we use a hierarchical structure and our novel sampling-based algorithm informed closedloop rapidly-exploring random trees (informed CL-RRTs) to efficiently repair the remaining part of the trajectory. We evaluate our approach with different traffic scenarios from the CommonRoad benchmark suite. The computational efficiency is demonstrated by comparing the computation times with those required when replanning the complete trajectory.
Autonomous vehicles must comply with traffic rules. However, most motion planners do not explicitly consider all relevant traffic rules. Once traffic rule violations of an initially-planned trajectory are detected, there is often not enough time to replan the entire trajectory. To solve this problem, we propose to repair the initial trajectory by investigating the satisfiability modulo theories paradigm. This framework makes it efficient to reason whether and how the trajectory can be repaired and, at the same time, determine the part along the trajectory that can remain unchanged. Moreover, the robustness of traffic rule satisfaction is used to formulate a convex optimization problem for generating rule-compliant trajectories. We compare our approach with trajectory replanning and demonstrate its usefulness with traffic scenarios from the CommonRoad benchmark suite and recorded data. The evaluation result shows that rule-compliant trajectory repairing is computationally efficient and widely applicable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.