Abstract-Numerical experiments for motion planning of road vehicles require numerous components: vehicle dynamics, a road network, static obstacles, dynamic obstacles and their movement over time, goal regions, a cost function, etc. Providing a description of the numerical experiment precise enough to reproduce it might require several pages of information. Thus, only key aspects are typically described in scientific publications, making it impossible to reproduce results-yet, reproducibility is an important asset of good science. Composable benchmarks for motion planning on roads (CommonRoad) are proposed so that numerical experiments are fully defined by a unique ID; all information required to reconstruct the experiment can be found on the CommonRoad website. Each benchmark is composed by a vehicle model, a cost function, and a scenario (including goals and constraints). The scenarios are partly recorded from real traffic and partly hand-crafted to create dangerous situations. We hope that CommonRoad saves researchers time since one does not have to search for realistic parameters of vehicle dynamics or realistic traffic situations, yet provides the freedom to compose a benchmark that fits one's needs.
Ensuring that autonomous vehicles do not cause accidents remains a challenge. We present the first formal verification technique to guaranteeing legal safety in arbitrary urban traffic situations. Legal safety denotes that autonomous vehicles never cause accidents although other traffic participants are allowed to perform any behaviour in accordance with traffic rules. Our technique serves as a safety layer for existing motion planning frameworks that provide intended trajectories for autonomous vehicles. We verify if intended trajectories comply with legal safety and provide fallback solutions in safety-critical situations. The benefits of our verification technique are demonstrated in critical urban scenarios, which have been recorded in real traffic. The autonomous vehicle executed only safe trajectories even when using an intended trajectory planner that was not aware of other traffic participants. Our results indicate that our online verification technique can drastically reduce the number of traffic accidents.Safety remains a major challenge for realizing autonomous vehicles. Unsafe decisions of autonomous vehicles can endanger human lives and cause tremendous economic loss in terms of product liability. While autonomous driving is becoming a reality, recent accidents involving autonomous driving systems have raised major concerns among various institutions [1], and
Abstract-Predicting the movement of other traffic participants is an integral part in the motion planning of most automated road vehicles. While simple predictions, e.g. based on assuming constant velocity, may suffice for deciding a driving strategy, predicting the set of all possible behaviors is required to ensure safe motion plans. In this work, we propose a novel tool for the latter problem based on reachability analysis: Set-Based Prediction Of Traffic Participants (SPOT). Our tool can predict the future occupancy of other traffic participants, including all possible maneuvers (e.g. full acceleration, full braking, and arbitrary lane changes), by considering physical constraints and assuming that the traffic participants abide by the traffic rules. However, we remove assumptions for each traffic participant individually as soon as a violation of a traffic rule is detected. Removal of assumptions automatically results in larger occupancies and thus a smaller drivable area for the ego vehicle, ensuring that the ego vehicle does not cause a collision during the time horizon of the prediction. Experimental results show that we obtain the set of future occupancies within a fraction of the prediction horizon. Our tool is available at spot.in.tum.de.
Falsification aims to disprove the safety of systems by providing counterexamples that lead to a violation of safety properties. In this work, we present two novel falsification methods to reveal safety flaws in adaptive cruise control (ACC) systems of automated vehicles. Our methods use rapidlyexploring random trees to generate motions for a leading vehicle such that the ACC under test causes a rear-end collision. By considering unsafe states and searching backward in time, we are able to drastically improve computation times and falsify even sophisticated ACC systems. The obtained collision scenarios reveal safety flaws of the ACC under test and can be directly used to improve the system's design. We demonstrate the benefits of our methods by successfully falsifying the safety of state-of-the-art ACC systems and comparing the results to that of existing approaches.
Provably safe motion planning for automated road vehicles must ensure that planned motions do not result in a collision with other traffic participants. This is a major challenge in autonomous driving, since the future behavior of other traffic participants is not known and since traffic participants are often hidden due to occlusions. In this work, we propose a formal setbased prediction that contains all acceptable future behaviors of both detected and potentially hidden traffic participants. Based on formalized traffic rules and nondeterministic motion models, we perform reachability analysis to predict the set of possible occupancies and velocities of vehicles, pedestrians, and cyclists. Real-world experiments with a test vehicle in various traffic situations demonstrate the applicability and real-time capability of our over-approximative prediction for both online verification and fail-safe trajectory planning. Even in congested, complex traffic scenarios, our forecasting approach enables self-driving vehicles to never cause accidents.
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.