Continuous-Time Gaussian Process Motion Planning via Probabilistic Inference

Abstract

We introduce a novel formulation of motion planning, for continuous-time trajectories, as probabilistic inference. We first show how smooth continuous-time trajectories can be represented by a small number of states using sparse Gaussian process (GP) models. We next develop an efficient gradient-based optimization algorithm that exploits this sparsity and GP interpolation. We call this algorithm the Gaussian Process Motion Planner (GPMP). We then detail how motion planning problems can be formulated as probabilistic inference on a factor graph. This forms the basis for GPMP2, a very efficient algorithm that combines GP representations of trajectories with fast, structure-exploiting inference via numerical optimization. Finally, we extend GPMP2 to an incremental algorithm, iGPMP2, that can efficiently replan when conditions change. We benchmark our algorithms against several sampling-based and trajectory optimization-based motion planning algorithms on planning problems in multiple environments. Our evaluation reveals that GPMP2 is several times faster than previous algorithms while retaining robustness. We also benchmark iGPMP2 on replanning problems, and show that it can find successful solutions in a fraction of the time required by GPMP2 to replan from scratch.

The International Journal of Robotics Research (IJRR), 2018, Volume 37, Issue 11

References in corpus (3)

• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Approximately Optimal Continuous-Time Motion Planning and Control via Probabilistic Inference
• Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments

Cited by in corpus (43)

• Multimodal Trajectory Optimization for Motion Planning
• Distributing Collaborative Multi-Robot Planning with Gaussian Belief Propagation
• A Fully-autonomous Framework of Unmanned Surface Vehicles in Maritime Environments using Gaussian Process Motion Planning
• Distributed Search Planning in 3-D Environments With a Dynamically Varying Number of Agents
• Habitat 2.0: Training Home Assistants to Rearrange their Habitat
• RMPflow: A Computational Graph for Automatic Motion Policy Generation
• Learning Implicit Priors for Motion Optimization
• A visual introduction to Gaussian Belief Propagation
• Stein Variational Model Predictive Control
• Fast Manipulability Maximization Using Continuous-Time Trajectory Optimization
• A Gaussian variational inference approach to motion planning
• A Survey on the Integration of Machine Learning with Sampling-based Motion Planning
• Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
• Geometric Fabrics for the Acceleration-based Design of Robotic Motion
• Planar Robot Casting with Real2Sim2Real Self-Supervised Learning
• Simultaneous Scene Reconstruction and Whole-Body Motion Planning for Safe Operation in Dynamic Environments
• Integrating DeepRL with Robust Low-Level Control in Robotic Manipulators for Non-Repetitive Reaching Tasks
• Motion planning in high-dimensional spaces
• The Differentiable Cross-Entropy Method
• Kernel Trajectory Maps for Multi-Modal Probabilistic Motion Prediction
• Manipulation Trajectory Optimization with Online Grasp Synthesis and Selection
• Entropy Regularized Motion Planning via Stein Variational Inference
• Batch and Incremental Kinodynamic Motion Planning using Dynamic Factor Graphs
• A Unified Method for Solving Inverse, Forward, and Hybrid Manipulator Dynamics using Factor Graphs
• Factor Graph-Based Planning as Inference for Autonomous Vehicle Racing
• Incrementally Stochastic and Accelerated Gradient Information mixed Optimization for Manipulator Motion Planning
• Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed
• MS2MP: A Min-Sum Message Passing Algorithm for Motion Planning
• Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
• Optimal Control for Structurally Sparse Systems using Graphical Inference
• Real-Time Adaptive Motion Planning via Point Cloud-Guided, Energy-Based Diffusion and Potential Fields
• The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation
• Global Tensor Motion Planning
• Multi-Modal Motion Planning Using Composite Pose Graph Optimization
• Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities
• Learning the Solution Manifold in Optimization and Its Application in Motion Planning
• Fast-reactive probabilistic motion planning for high-dimensional robots
• Probabilistic approach to feedback control enhances multi-legged locomotion on rugged landscapes
• A White-Noise-On-Jerk Motion Prior for Continuous-Time Trajectory Estimation on SE(3)
• Approximate Topological Optimization using Multi-Mode Estimation for Robot Motion Planning
• BOW: Bayesian Optimization over Windows for Motion Planning in Complex Environments
• Efficient Iterative Proximal Variational Inference Motion Planning
• Multi-agent Gaussian Process Motion Planning via Probabilistic Inference