Hybrid Imitation-Learning Motion Planner for Urban Driving
This work addresses the safety-critical problem of motion planning for urban self-driving vehicles, representing an incremental improvement by integrating existing techniques.
The paper tackles the challenge of ensuring safe closed-loop driving in learning-based motion planners by proposing a hybrid planner that combines a learning-based component for human-like trajectory generation with an optimization-based component for safety refinement. The model balances safety and human-likeness, validated through simulation and real-world deployment in self-driving vehicles.
With the release of open source datasets such as nuPlan and Argoverse, the research around learning-based planners has spread a lot in the last years. Existing systems have shown excellent capabilities in imitating the human driver behaviour, but they struggle to guarantee safe closed-loop driving. Conversely, optimization-based planners offer greater security in short-term planning scenarios. To confront this challenge, in this paper we propose a novel hybrid motion planner that integrates both learning-based and optimization-based techniques. Initially, a multilayer perceptron (MLP) generates a human-like trajectory, which is then refined by an optimization-based component. This component not only minimizes tracking errors but also computes a trajectory that is both kinematically feasible and collision-free with obstacles and road boundaries. Our model effectively balances safety and human-likeness, mitigating the trade-off inherent in these objectives. We validate our approach through simulation experiments and further demonstrate its efficacy by deploying it in real-world self-driving vehicles.