Real-time Motion Planning Framework for Autonomous Vehicles with Learned Committed Trajectory Distribution

This study proposes a real-time motion planning framework that leverages the prediction of a portion of the optimal trajectory for sampling-based anytime planning algorithms. Existing algorithms predict the entire optimal path and bias random samples toward it for fast path planning. However, these algorithms may not be suitable for real-time frameworks because the bias-sampling strategy should consider the sequential nature of real-time execution. Therefore, the proposed algorithm predicts a portion of the optimal path, known as the committed trajectory, step by step as a probability distribution using a neural network. This distribution is then used in a sampling-based anytime planning algorithm as a non-stationary way of biasing random samples. The proposed algorithm can sequentially plan the near-optimal motion, allowing the vehicle to reach the desired goal pose in a timely and accurate manner. In various test parking scenarios, the proposed algorithm reduces the parking time by approximately 38% compared with conventional motion planning algorithms and by 10% compared with another real-time framework that biases samples toward the entire optimal trajectory.