Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems

  title={Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems},
  author={Yashwanth Kumar Nakka and Anqi Liu and Guanya Shi and Anima Anandkumar and Yisong Yue and Soon-Jo Chung},
Learning-based control algorithms require data collection with abundant supervision for training. Safe exploration algorithms ensure the safety of this data collection process even when only partial knowledge is available. We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained stochastic optimal control with dynamics learning and feedback control. We derive an iterative convex optimization algorithm that solves an \underline{Info}rmation… Expand
10 Citations

Figures from this paper

Closing the Closed-Loop Distribution Shift in Safe Imitation Learning
  • 4
  • PDF
Limits of Probabilistic Safety Guarantees when Considering Human Uncertainty
  • PDF
Robust Controller Design for Stochastic Nonlinear Systems via Convex Optimization
  • 8
  • PDF
Learning Unstable Dynamics with One Minute of Data: A Differentiation-based Gaussian Process Approach
  • PDF
Certainty Equivalent Perception-Based Control
  • 4
  • PDF


Learning-Based Model Predictive Control for Safe Exploration
  • 150
  • PDF
Trajectory Optimization for Chance-Constrained Nonlinear Stochastic Systems
  • 6
  • PDF
Robust Regression for Safe Exploration in Control
  • 23
  • PDF
Iterative Risk Allocation: A new approach to robust Model Predictive Control with a joint chance constraint
  • M. Ono, B. Williams
  • Mathematics, Computer Science
  • 2008 47th IEEE Conference on Decision and Control
  • 2008
  • 103
  • PDF
Chance-Constrained Optimal Path Planning With Obstacles
  • 178
  • PDF
Safe Exploration of State and Action Spaces in Reinforcement Learning
  • 86
  • PDF
Model Predictive Control of Swarms of Spacecraft Using Sequential Convex Programming
  • 162
  • PDF
Stochastic model predictive control with active uncertainty learning: A Survey on dual control
  • A. Mesbah
  • Computer Science
  • Annu. Rev. Control.
  • 2018
  • 42
  • PDF