Reaching through latent space: From joint statistics to path planning in manipulation

Journal article

We present a novel approach to path planning for robotic manipulators, in which paths are produced via iterative optimisation in the latent space of a generative model of robot poses. Constraints are incorporated through the use of constraint satisfaction classifiers operating on the same space. Optimisation leverages gradients through our learned models that provide a simple way to combine goal reaching objectives with constraint satisfaction, even in the presence of otherwise non-differentiable constraints. Our models are trained in a task-agnostic manner on randomly sampled robot poses. In baseline comparisons against a number of widely used planners, we achieve commensurate performance in terms of task success, planning time and path length, performing successful path planning with obstacle avoidance on a real 7-DoF robot arm.

Authors: Hung, C-M; Zhong, S; Goodwin, W; Parker Jones, O; Engelcke, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Journal: IEEE Robotics and Automation Letters
• Volume: 7
• Issue: 2
• Pages: 5334-5341
• Publication date: 2022-02-23
• DOI: 10.1109/lra.2022.3152697
• EISSN: 2377-3766
• Language: English
• Keywords: deep learning in grasping and manipulation; representation learning; constrained motion planning; FFR; optimization and optimal control