Combining Coarse and Fine Physics for Manipulation using Parallel-in-Time Integration

Abstract

We present a method for fast and accurate physics-based predictions during non-prehensile manipulation planning and control. Given an initial state and a sequence of controls, the problem of predicting the resulting sequence of states is a key component of a variety of model-based planning and control algorithms. We propose combining a coarse (i.e. computationally cheap but not very accurate) predictive physics model, with a fine (i.e. computationally expensive but accurate) predictive physics model, to generate a hybrid model that is at the required speed and accuracy for a given manipulation task. Our approach is based on the Parareal algorithm, a parallel-in-time integration method used for computing numerical solutions for general systems of ordinary differential equations. We adapt Parareal to combine a coarse pushing model with an off-the-shelf physics engine to deliver physics-based predictions that are as accurate as the physics engine but run in substantially less wall-clock time, thanks to parallelization across time. We use these physics-based predictions in a model-predictive-control framework based on trajectory optimization, to plan pushing actions that avoid an obstacle and reach a goal location. We show that with hybrid physics models, we can achieve the same success rates as the planner that uses the off-the-shelf physics engine directly, but significantly faster. We present experiments in simulation and on a real robotic setup. Videos are available here: https://youtu.be/5e9oTeu4JOU

International Symposium on Robotics Research (ISRR), 2019

References in corpus (9)

• Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds
• Model Predictive Path Integral Control using Covariance Variable Importance Sampling
• Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
• Uncertainty Averse Pushing with Model Predictive Path Integral Control
• Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data
• Feedback Control of the Pusher-Slider System: A Story of Hybrid and Underactuated Contact Dynamics
• Shared Memory Pipelined Parareal
• Efficient Computation of Higher-Order Variational Integrators in Robotic Simulation and Trajectory Optimization
• Pushing Fast and Slow: Task-Adaptive Planning for Non-prehensile Manipulation Under Uncertainty

Cited by in corpus (4)

• GRiD: GPU-Accelerated Rigid Body Dynamics with Analytical Gradients
• Robust Physics-Based Manipulation by Interleaving Open and Closed-Loop Execution
• Time-parallel simulation of the Schrödinger Equation
• Human-like Planning for Reaching in Cluttered Environments