ROCH-Risk-averse Optimal Control via Homotopy

Consortium: Riccardo Bonalli (Project Investigator), CNRS and Université Paris-Saclay; Brandon Amos; Alessio Iovine, CNRS and Université Paris-Saclay; Marco Pavone, Stanford University.

Goal: this ANR JCJC project aims at developing both original reinforcement learning techniques to design reliable control models and novel stochastic optimal control tools to tackle non-convex risk-averse stochastic optimal control problems. The ultimate objective is to leverage and combine such new methods to devise a reliable and scalable algorithm called ROCH, for efficient and safe-against-uncertainty deployment of autonomous systems.



  1. A. C. Morelli, C. Giordano, R. Bonalli, and F. Topputo, Characterization of Singular Arcs in Spacecraft Trajectory Optimization. Submitted. Pdf file.
  2. G. Velho, J. Auriol, and R. Bonalli, A Gradient Descent-Ascent Method for Continuous-Time Risk-Averse Optimal Control. Submitted. Pdf file.
  3. R. Bonalli and A. Rudi, Non-Parametric Learning of Stochastic Differential Equations with Fast Rates of Convergence. Submitted. Pdf file.
  4. C. Leparoux, R. Bonalli, B. Hérissé, and F. Jean, Statistical Linearization for Robust Motion Planning. Submitted. Pdf file.
  5. T. Lew, R. Bonalli, and M. Pavone, Sample Average Approximation for Stochastic Programming with Equality Constraints. Submitted. Pdf file.
  6. T. Lew, R. Bonalli, and M. Pavone, Risk-Averse Trajectory Optimization via Sample Average Approximation. Accepted in IEEE Robotics and Automation Letters. Pdf file.
  7. R. Bonalli, C. Leparoux, B. Hérissé, and F. Jean, On the Accessibility and Controllability of Statistical Linearization for Stochastic Control: Algebraic Rank Conditions and their Genericity. Mathematical Control and Related Fields, Early Access (2023). Pdf file.
  8. G. Velho, R. Bonalli, J. Auriol, and I. Boussaada, Mean-Covariance Steering of a Linear Stochastic System with Input Delay and Additive Noise. Submitted. Pdf file.