Learning from Experience for Rapid Generation of Local Car Maneuvers

Abstract

Being able to rapidly respond to the changing scenes and traffic situations by generating feasible local paths is of pivotal importance for car autonomy. We propose to train a deep neural network (DNN) to plan feasible and nearly-optimal paths for kinematically constrained vehicles in small constant time. Our DNN model is trained using a novel weakly supervised approach and a gradient-based policy search. On real and simulated scenes and a large set of local planning problems, we demonstrate that our approach outperforms the existing planners with respect to the number of successfully completed tasks. While the path generation time is about 40 ms, the generated paths are smooth and comparable to those obtained from conventional path planners.

References in corpus (4)

• Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs
• Systematic evaluation of CNN advances on the ImageNet
• Batch Informed Trees (BIT*): Informed Asymptotically Optimal Anytime Search
• Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees

Cited by in corpus (1)

• Speeding up deep neural network-based planning of local car maneuvers via efficient B-spline path construction