Dynamically constrained motion planning networks for non-holonomic robots

Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020

Jacob J Johnson, Linjun Li, Fei Liu, Ahmed H Qureshi, Michael C Yip

Abstract: Reliable real-time planning for robots is essential in today’s rapidly expanding automated ecosystem. In such environments, traditional methods that plan by relaxing constraints become unreliable or slow-down for kinematically constrained robots. This paper describes the algorithm Dynamic Motion Planning Networks (Dynamic MPNet), an extension to Motion Planning Networks, for non-holonomic robots that address the challenge of real-time motion planning using a neural planning approach. We propose modifications to the training and planning networks that make it possible for real-time planning while improving the data efficiency of training and trained models’ generalizability. We evaluate our model in simulation for planning tasks for a non-holonomic robot. We also demonstrate experimental results for an indoor navigation task using a Dubins car.

Johnson et al. (2020) Dynamically constrained motion planning networks for non-holonomic robots, Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6937-6943.

Pub Link: http://ieeexplore.ieee.org/abstract/document/9341283/
arXiv: