Neural Manipulation Planning on Constraint Manifolds

Abstract

The presence of task constraints imposes a significant challenge to motion planning. Despite all recent advancements, existing algorithms are still computationally expensive for most planning problems. In this paper, we present Constrained Motion Planning Networks (CoMPNet), the first neural planner for multimodal kinematic constraints. Our approach comprises the following components: i) constraint and environment perception encoders; ii) neural robot configuration generator that outputs configurations on/near the constraint manifold(s), and iii) a bidirectional planning algorithm that takes the generated configurations to create a feasible robot motion trajectory. We show that CoMPNet solves practical motion planning tasks involving both unconstrained and constrained problems. Furthermore, it generalizes to new unseen locations of the objects, i.e., not seen during training, in the given environments with high success rates. When compared to the state-of-the-art constrained motion planning algorithms, CoMPNet outperforms by order of magnitude improvement in computational speed with a significantly lower variance.

This is the preprint version of the paper published at IEEE Robotics and Automation Letters 2020

References in corpus (4)

• Informed RRT*: Optimal Sampling-based Path Planning Focused via Direct Sampling of an Admissible Ellipsoidal Heuristic
• Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs
• Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environments
• Trajectory Optimization on Manifolds: A Theoretically-Guaranteed Embedded Sequential Convex Programming Approach

Cited by in corpus (6)

• A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches
• Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
• Motion Memory: Leveraging Past Experiences to Accelerate Future Motion Planning
• Learning-based Initialization of Trajectory Optimization for Path-following Problems of Redundant Manipulators
• Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities
• Local Path Optimization in The Latent Space Using Learned Distance Gradient