Category: Robotics
-
Clinical Validation and Computer Vision Upgrade of “SkyTrace”: A Webcam-Based Rehabilitation Game for Stroke Patients
Contacts: Marta Gandolla, Andrea Dal Prete Location: Politecnico di Milano (Bovisa Campus) / SkyTrace R&D Lab & Villa Beretta Rehabilitation Center (Costa Masnaga, LC, Italy) Duration: 6 months Target Degrees: Biomedical Engineering, Computer Science & Engineering, Mechatronics & Control Engineering Motivation of the study: Effective neuromotor recovery following a cerebrovascular event requires high-dose, task-oriented rehabilitation to induce…
-
Cooperative-Competitive Autonomous Racing through Joint Latent Imagination
Introduction Multi-agent autonomous racing requires agents to balance individual performance, cooperation with teammates and competition against opponents. In a 2-vs-2 setting, effective decisions may involve coordinated overtaking, defensive blocking or sacrificing short-term individual performance to improve the team outcome. Model-based reinforcement learning provides a promising framework for this problem by learning a predictive world model…
-
Environment-Aware Collision Avoidance for Multi-Agent Navigation
Introduction Safe autonomous navigation requires reasoning not only about how other agents may move, but also about which maneuvers are compatible with the surrounding environment. Hamilton–Jacobi (HJ) reachability can provide a framework for collision avoidance under worst-case interactions. Environmental constraints can already be included in HJ formulations, but combining geometry and multi-agent interaction can significantly…
-
Integration of an Exoskeleton, a Humanoid Robot, and the RoboMate Platform: A Proof of Concept for Coordinated Parkinson’s Exercises
Prof. Loris Roveda: loris.roveda@polimi.it
-
Reduced-order aeroelastic modeling and control of inflatable multirotor drones
Inflatable and soft structures offer interesting opportunities for the development of lightweight, compact, and deployable aerial vehicles. In particular, multirotor drones based on inflatable structural frames could combine conventional propulsion and control systems with lightweight and compliant supporting structures. Such configurations may enable drones that can be compactly stored and rapidly deployed, while also providing…
-
Aerodynamics of drone flight in complex wind farm flows (no CFD)
The use of drones in wind farms offers significant opportunities for automated inspection, measurements of the atmospheric wind, and the transport of tools and equipment. In these applications, drones may operate close to wind turbines and therefore encounter a highly complex aerodynamic environment characterized by atmospheric turbulence, wind shear, and the unsteady wakes generated by…
-
Physics-based aerodynamic modeling of drone formation flight (no CFD)
The rapid growth of autonomous aerial systems is driving the development of drone swarms capable of performing cooperative missions such as environmental monitoring, infrastructure inspection, search and rescue, and parcel delivery. As these applications increasingly rely on multiple drones operating in close proximity, aerodynamic interactions between their rotor wakes become an important factor affecting flight…
-
Control of a Soft Mackerel-inspired Robot
This thesis focuses on the development of the control algorithm for a mackerel-inspired robot. The robot has a rigid head containing sensors and motors, a soft body made of silicone rubber with a TPU-made backbone, and a compliant caudal fin. The objective of this thesis is to develop a control algorithm using ROS2 to enable…
-
Bridging Simulation and Reality for Autonomous Underwater Vehicles
Autonomous Underwater Vehicles (AUV) are subject to highly non-linear hydrodynamic forces, significant parametric uncertainty, and unpredictable environmental disturbances, all of which make robust low-level control a persistent open challenge. This thesis investigates control strategies for AUV motion control with a focus on robustness, the ability of a controller to maintain acceptable performance despite uncertainty in…
-
Sensorless Transformer for Interaction Force Prediction and Estimation
While recent work has shown that generative AI models, like transformers, can be used to predict future interaction forces, given past recorded data, including recorded forces, many platforms lack force sensors or cannot reliably record past forces. To bridge this gap, this thesis aims to augment a transformer model so it can estimate current interaction…