A5071265848- Robotic Path Planning Algorithms
- Control and Dynamics of Mobile Robots
- Vehicle Dynamics and Control Systems
- Robotic Locomotion and Control
- Robot Manipulation and Learning
- Dynamics and Control of Mechanical Systems
- Robotic Mechanisms and Dynamics
- Reinforcement Learning in Robotics
- Robotics and Sensor-Based Localization
- Distributed Control Multi-Agent Systems
- Hydraulic and Pneumatic Systems
- Control Systems and Identification
- Social Robot Interaction and HRI
- Advanced Control Systems Optimization
- Human-Automation Interaction and Safety
- Infrastructure Maintenance and Monitoring
- Manufacturing Process and Optimization
- Occupational Health and Safety Research
- Robotics and Automated Systems
- Transportation and Mobility Innovations
- Advanced Control Systems Design
- Neural Networks and Applications
- Soft Robotics and Applications
- Soil Mechanics and Vehicle Dynamics
- Guidance and Control Systems
CEA LIST
2016-2024
CEA Paris-Saclay
2016-2024
Université Paris-Saclay
2021-2024
Commissariat à l'Énergie Atomique et aux Énergies Alternatives
2015-2024
Integra (United States)
2019
Direction de la Recherche Technologique
2019
Laboratoire d’Ingénierie des Systèmes Physiques et Numériques
2019
Laboratoire de Recherche en Informatique
2017
Robosoft (France)
2008-2015
Maison de la Simulation
2015
Human–robot collaboration is currently one of the frontiers industrial robot implementation. In parallel, use robots and robotic devices increasing in several fields, substituting humans “4D”—dull, dirty, dangerous, delicate—tasks, such a trend boosted by recent need for social distancing. New challenges safety assessment verification arise, due to both closer human–robot interaction, common different application domains, broadening user audience, which now very diverse. The present paper...
A robust dynamic feedback controller is designed and implemented, based on the model of six-wheel skid-steering RobuROC6 robot, performing high speed turns. The control inputs are respectively linear velocity yaw angle. main object this paper to elaborate a sliding mode controller, proved be enough ignore knowledge forces within wheel-soil interaction, in presence phenomena ground level fluctuations. Finally, 3D simulation performed with an accurate physical engine evaluate efficiency law.
This paper proposes an improvement of a motion planning approach and modified model predictive control (MPC) for solving the navigation problem team dynamical wheeled mobile robots in presence obstacles realistic environment. Planning is performed by distributed receding horizon algorithm where constrained optimization problems are numerically solved each prediction time-horizon. allows multi-robot system with asynchronous communication while avoiding collisions minimizing travel time robot....
This paper deals with design and implementation of a stabilization algorithm for car like robot performing high speed turns. The control such kind system is rather difficult because the complexity physical wheel- soil interaction model. In this paper, it planned to analyze complex dynamic model process elaborate only based on measurement yaw rate. Finally, 3D simulation performed evaluate efficiency designed algorithm.
Robots are required to perform more and complicated tasks, which raises the requirement of intelligent planning algorithms.As a domain having been explored for decades, task motion (TAMP) methods have achieved significant results, but several challenges remain be solved.This paper summarizes development TAMP from solving objectives, simulation environments, remaining limitations.In particular, it compares different environments used in tasks aiming provide practical guide overview beginners.
This paper is focused on the problem of accurate and reliable path tracking control a 4-wheels car-like mobile robot moving off-road at high speed. Dynamic extended kinematic models that take into account effects wheel skidding are presented. Based model, an adaptive predictive controller for derived. law combined to stabilization algorithm yaw motion, based dynamic model modulation driven forces. The overall architecture experimentally evaluated slipping terrain. Results demonstrate...
Ensuring a safe online motion planning despite large number of moving agents is the problem addressed in this paper. Collision avoidance achieved without communication between and global localization system. The proposed solution modification Hybrid Reciprocal Velocity Obstacles (HRVO) combined with tracking error estimation, order to adapt Obstacle paradigm kinodynamic constraints unreliable velocity estimates. This solution, evaluated simulation real test scenario three dynamic unicycle...
This paper proposes a new approach for online control law gains adaptation, through the use of neural networks and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm, in order to optimize behavior robot with respect an objective function. The network considered takes as input current observed state well its uncertainty, provides output gains. It is trained, using CMA-ES on simulator reproducing vehicle dynamics. Then, it tested real conditions agricultural mobile at different...
This paper proposes the real-time implementation of an algorithm for collision-free motion planning based on a receding horizon approach, navigation team mobile robots in presence obstacles different shapes. The method is simulated with three robots. Impact parameters studied regard to computation time, obstacle avoidance and travel time.
This paper proposes a new approach for feature importance of neural networks and subsequently methodology to determine useful sensor information in high performance controllers, using trained network that predicts the quasi-optimal gain real time. The is Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm, order lower given objective function. important robotic control are determined described methodology. Then proposed improvement tested law given, compared with network's...
During the off-road path following of a wheeled mobile robot in presence poor grip conditions, longitudinal velocity should be limited order to maintain safe navigation with tracking errors, while at same time being high enough minimize travel time. Thus, this paper presents new approach online speed fluctuation, capable limiting lateral error below given threshold, maximizing velocity. This is accomplished using neural network trained reinforcement learning method. modulation done...
Abstract This paper presents the full implementation of a mobile robotic manipulator moving probe inside steel cylinder concrete pipes (SCCP) for corrosion assessment. Mechanical prototype based on an off-the-shelf base and custom-designed manipulator, control monitoring software architecture, posture manipulation SCCP are presented. Simulations testing under realistic operating conditions demonstrate reliable solution providing repeatable results with high positioning accuracy.
This paper presents the definition of a teleoperated robotic system for non-destructive corrosion inspection Steel Cylinder Concrete Pipes (SCCP) from inside. A general description in-pipe environment and state art navigation solutions are exposed, with zoom on characteristics SCCP case interest (pipe dimensions, curves, slopes, humidity, payload, etc.). Then, two specific steel measurement techniques described. In order to operate them, several possible architectures (mobile platform...