10 papers
Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation
Valerio Belli, Valerio Modugno, Enrico Mingo Hoffman +1
Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process. Motion…
Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization
Marcelina Marjankowska, Valerio Modugno, Paolo Barucca
Hessian spectral properties are a standard tool in analysing neural-network training, with eigenvalues linked to sharpness, generalization, and optimization dynamics. Eigenvalues q…
Stable Transformer-Actor-Critic Model Predictive Control: A Contraction Analysis Approach
Antonio Marino, Valerio Modugno, Marco Cognetti
Actor-Critic Model Predictive Control (MPC) effectively addresses complex, non-convex control problems, but guaranteeing the closed-loop stability of sequence-based learning models…
A Progress-Aware Leader-Follower Midair Docking System for Dual-Drone Aerial Manipulation
Yifan Cai, Jan Ming Kevin Tan, Xiangqi Li +3
Reliable midair docking between small unmanned aerial vehicles (UAVs) is essential for modular aerial cooperation and manipulation, but it requires precise relative-pose control an…
An Aerial Manipulator for Perception-Driven Flower Targeting Toward Contactless Pollination in Vertical Farming
Chenzhe Jin, Zhuohang Wu, Yifan Cai +4
The decline of natural pollinators has created a major challenge for crop production in controlled indoor agriculture, particularly in vertical farming environments where natural i…
Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers
Tommaso Belvedere, Michael Ziegltrum, Giulio Turrisi +1
Model Predictive Path Integral control is a powerful sampling-based approach suitable for complex robotic tasks due to its flexibility in handling nonlinear dynamics and non-convex…