5 papers
VAMPS: Visual and Motor Policies from Sampling-Based Planning
Mohamed Yassine Kabouri, Pietro Noah Crestaz, Quang-Nam Nguyen +3
Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Motor Policie…
CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning
Pietro Noah Crestaz, Mohamed Yassine Kabouri, Nicolas Mansard +1
Model-based reinforcement learning (MBRL) is a family of RL methods that learn a model of the environment and use it for action selection, making it well suited to robotics due to…
COSMIK-MPPI: Scaling Constrained Model Predictive Control to Collision Avoidance in Close-Proximity Dynamic Human Environments
Ege Gursoy, Maxime Sabbah, Arthur Haffemayer +5
Ensuring safe physical interaction between torque-controlled manipulators and humans is essential for deploying robots in everyday environments. Model Predictive Control (MPC) has…
CACTO-BIC: Scalable Actor-Critic Learning via Biased Sampling and GPU-Accelerated Trajectory Optimization
Elisa Alboni, Pietro Noah Crestaz, Elias Fontanari +1
Trajectory Optimization (TO) and Reinforcement Learning (RL) offer complementary strengths for solving optimal control problems. TO efficiently computes locally optimal solutions b…
Constrained Trajectory Optimization for Hybrid Dynamical Systems
Pietro Noah Crestaz, Gokhan Alcan, Ville Kyrki
Hybrid dynamical systems pose significant challenges for effective planning and control, especially when additional constraints such as obstacle avoidance, state boundaries, and ac…