- Robotic Locomotion and Control
- Prosthetics and Rehabilitation Robotics
- Muscle activation and electromyography studies
- Context-Aware Activity Recognition Systems
- Robot Manipulation and Learning
- Biomedical and Engineering Education
- Stroke Rehabilitation and Recovery
- Autonomous Vehicle Technology and Safety
- Urban and Freight Transport Logistics
- Robotics and Sensor-Based Localization
- Teleoperation and Haptic Systems
- Advanced Vision and Imaging
- Human-Automation Interaction and Safety
- IoT-based Smart Home Systems
- Robotics and Automated Systems
- Transportation and Mobility Innovations
- Social Robot Interaction and HRI
- Advanced Optical Network Technologies
- Smart Parking Systems Research
- Robotic Mechanisms and Dynamics
- Advanced Software Engineering Methodologies
- Biomimetic flight and propulsion mechanisms
- Soil Mechanics and Vehicle Dynamics
- IoT and Edge/Fog Computing
- Robotic Path Planning Algorithms
Politecnico di Milano
2009-2024
VersuchsStollen Hagerbach (Switzerland)
2023
National Research Council
2015-2018
Italian Institute of Technology
2011-2016
University of Trento
2012-2016
Indoor localization and position tracking are essential to support applications services for ambient-assisted living. While the problem of indoor is still open already quite complex per se, in large public places, additional issues cost, accuracy, scalability arise. In this paper, estimation technique developed within project devices assisted living (DALi) described, analyzed through simulations, finally validated by means a variety experiments on field. The goal DALi design robotic wheeled...
This paper presents a novel whole-body torque-control concept for humanoid walking robots. The presented Whole-Body Motion Control (WBMC) system combines several unique concepts. First, computationally efficient gravity compensation algorithm floating-base systems is derived. Second, balancing approach proposed, which exploits set of fundamental physical principles from rigid multi-body dynamics, such as the overall linear and angular momentum, minimum effort formulation. Third, attractors...
Research on humanoid locomotion made significant improvements over the last years. In most cases, though, gait of state-of-the-art robots is still far from being human-like due to two main reasons. These are, mechanical incompatibilities between human and engineered platforms, lack clear understanding highly complex walking motion itself. This work attempts address latter by using a novel method construct trajectories for robot based kinematic Motion Primitives (kMPs) derived humans...
Human neuromotor capabilities guarantee a wide variety of motions. A full understanding human motion can be beneficial for rehabilitation or performance enhancement purposes, its reproduction on artificial systems like robots. This work aims at describing the complexity in reduced dimensionality, by means kinematic Motion Primitives (kMPs). set five invariant kMPs are identified periodic motions, and two discrete It is shown how these sets combined to synthesize more complex as simultaneous...
Many applications in mobile robotics require the localization of robot with respect to boundary a path (e.g., lane marker) and reconstruction front robot. The former can be used as basis for reactive control scheme that drives along specified latter is plan its future motion. Our solution these problems relies on camera mounted chassis pointing headway. relevant elements image grabbed from (i.e., lines delimiting path) are robustly extracted projected into field-of-view virtual looking over...
Research in humanoid robotics recent years has led to significant advances terms of the ability walk and even run. Yet, despite general achievements locomotion control, energy efficiency is still one important area that requires further attention, especially as it major steeping stones leading increased autonomy. This paper examines, quantifies, energetic benefits introducing passive compliance into bipedal using COMAN, an intrinsically COmpliant huMANoid robot. The novelty method proposed...
Whole-body control (WBC) systems represent a wide range of complex movement skills in the form low-dimensional task descriptors which are projected on to robot’s actuator space. Using these methods allow exploit full capabilities entire body redundant, floating-base robots compliant multi-contact interaction with environment, execute any single and simultaneous multiple tasks. This paper presents an attractor-based whole-body motion (WBMC) system, developed for torque-control robots. The...
Models are used in control domains for early validation of system properties, using simulation or formal verification, and the automatic generation a software implementation. We propose an approach which functional model controls is matched to execution platform through intermediate mapping model, that represents tasks communication messages. The (partly) developed Simulink code generated each subsystem. Next, abstract view imported SysML. Using SysML, created, implementation subsystems as...
We compare two different solutions to guide an older adult along a safe path using robotic walking assistant (the c-Walker). The are based on tactile or acoustic stimuli, respectively, and suggest direction of motion that the user is supposed take her own will. describe technological basis for hardware components, show specialised following algorithms each solutions. paper reports extensive validation activity, with quantitative qualitative analysis.
This paper presents an analysis of the relation between effort and gravitational stiffness, two physical measures that depend on configuration robot. It is shown whenever stiffness maximized, indirectly minimized. A minimum attractor controls presented. together with to zero joint momentum guarantee balance maintenance. The novel implementation attractor-based Whole-body Motion Control (WBMC) System experimentally tested: first simple models, finally full-body humanoid robot COMAN in a simulation.
A popular technique to localise a vehicle on the lane is by using camera mounted chassis pointing headway. This approach requires: an image processing algorithm extract relevant information from scene and estimation estimate position of boundary. In this paper, we address both problems simultaneously defining robust that simplifies enables localization in 3D space. The accuracy proposed solution evaluated simulations experiments.
The estimation of internal pressure in trains is crucial for designing and operating vehicles safely, ensuring both passenger comfort structural integrity.However, modeling presents challenges due to various uncertainties.This study focuses on estimating by evaluating different approaches based experimental measurements conducted a full-scale train travelling track with tunnels presence.To determine the parameters models efficiently, rapid effective method employed.Modeled pressures are then...
Reports on the activities and research conducted by IEEE Robotics Automation Society Technical Committee Whole-Body Control (WBC-TC) that was established in 2014.
In this paper, we propose several solutions to guide an older adult along a safe path using robotic walking assistant (the c-Walker). We consider four different possibilities execute the task. One of them is mechanical, with c-Walker playing active role in setting course. The other ones are based on tactile or acoustic stimuli, and suggest direction motion that user supposed take her own will. describe technological basis for hardware components implementing solutions, show specialized...