Dodging the Moose: Experimental Insights in Real-Life Automated Collision Avoidance
🤖 AI Summary
This work addresses the challenge of real-time collision avoidance in autonomous driving when encountering sudden static obstacles—such as in moose test scenarios—where nonlinear model predictive control (MPC) often fails due to high computational complexity. To overcome this limitation, the authors propose a hybrid planning framework that integrates a human-like feedforward planner with a maximum-steering-maneuver strategy. When the MPC becomes infeasible or suffers from a poor initial guess, the system automatically switches to an emergency evasion mode based on the maximum steering maneuver. The approach was validated experimentally on the FPEV2-Kanon electric vehicle across a range of speeds and urgency levels, demonstrating consistently stable obstacle avoidance. The method significantly improves both real-time performance and feasibility compared to existing MPC-based motion planning techniques.
Application Category
📝 Abstract
The sudden appearance of a static obstacle on the road, i.e. the moose test, is a well-known emergency scenario in collision avoidance for automated driving. Model Predictive Control (MPC) has long been employed for planning and control of automated vehicles in the state of the art. However, real-time implementation of automated collision avoidance in emergency scenarios such as the moose test remains unaddressed due to the high computational demand of MPC for evasive action in such hazardous scenarios. This paper offers new insights into real-time collision avoidance via the experimental imple- mentation of MPC for motion planning after a sudden and unexpected appearance of a static obstacle. As the state-of-the-art nonlinear MPC shows limited capability to provide an acceptable solution in real-time, we propose a human-like feed-forward planner to assist when the MPC optimization problem is either infeasible or unable to find a suitable solution due to the poor quality of its initial guess. We introduce the concept of maximum steering maneuver to design the feed-forward planner and mimic a human-like reaction after detecting the static obstacle on the road. Real-life experiments are conducted across various speeds and level of emergency using FPEV2-Kanon electric vehicle. Moreover, we demonstrate the effectiveness of our planning strategy via comparison with the state-of- the-art MPC motion planner.
Problem
Research questions and friction points this paper is trying to address.
collision avoidance
moose test
real-time implementation
automated driving
static obstacle
Innovation
Methods, ideas, or system contributions that make the work stand out.
Model Predictive Control
feed-forward planner
maximum steering maneuver
real-time collision avoidance
moose test
🔎 Similar Papers
No similar papers found.
