# Learning from Experience for Rapid Generation of Local Car Maneuvers

arXiv: https://arxiv.org/abs/2012.03707 · HTML: https://mlsanity.com/paper/2012.03707/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 4 of 4)

- [Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks](https://mlsanity.com/paper/2301.04330/) (2023)
- [Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning](https://mlsanity.com/paper/2408.14063/) (2024)
- [Search-Based Task and Motion Planning for Hybrid Systems: Agile Autonomous Vehicles](https://mlsanity.com/paper/2301.10384/) (2023)
- [Speeding up deep neural network-based planning of local car maneuvers via efficient B-spline path construction](https://mlsanity.com/paper/2203.06963/) (2022)

## Abstract (arXiv)

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.