A5046931302- Evacuation and Crowd Dynamics
- Human Motion and Animation
- Artificial Intelligence in Games
- Educational Games and Gamification
- Music Technology and Sound Studies
- Music and Audio Processing
- Robot Manipulation and Learning
- Multi-Agent Systems and Negotiation
- Tactile and Sensory Interactions
- Hand Gesture Recognition Systems
- Virtual Reality Applications and Impacts
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Advanced Optical Imaging Technologies
- Traffic Prediction and Management Techniques
- Manufacturing Process and Optimization
- Robotic Mechanisms and Dynamics
- Resource-Constrained Project Scheduling
- Computer Graphics and Visualization Techniques
- Auction Theory and Applications
- 3D Shape Modeling and Analysis
- Human Pose and Action Recognition
- Robotics and Automated Systems
- Teleoperation and Haptic Systems
- Topic Modeling
Airbus (France)
2021-2023
Airbus (Germany)
2021
National Institute of Advanced Industrial Science and Technology
2018-2019
Centro de Estudios y Experimentación de Obras Públicas
2018
Shinshu University
2015-2016
National Institute of Informatics
2012-2016
Manipulation of Deformable Linear Objects is a difficult task for robots in real environments due to requiring high computational power order predict accurately the object's deformation. Taking advantage on proliferation cheap and easy use 3D environment simulation engines, this paper we propose method manipulation planning deformable linear objects which uses physics engine predicting object behavior, calculate possible outcomes manipulation. We implemented system designed generate plan...
Deformable Linear Object manipulation stands as an important aspect of robot operation, with wide applications in industrial and daily life. However, it is also a difficult task to perform; the problems we encounter are related object's intrinsic physical characteristics that require complex prediction order properly interact them, like its flexibility or elasticity. One approaches available researchers for obtaining plans consists recreating object virtual environment simulating...
Virtual environments offer an ideal setting to develop intelligent training applications. Yet, their ability support complex procedures depends on the appropriate integration of knowledge-based techniques and natural interaction. In this article, we describe implementation rehearsal system for biohazard laboratory procedures, based real-time instantiation task models from trainee’s actions. A virtual has been recreated using Unity3D engine, in which users interact with objects keyboard/mouse...
In industrial contexts, effective workforce allocation is crucial for operational efficiency. This paper presents an ongoing project focused on developing a decision-making tool designed allocation, emphasising the explainability to enhance its trustworthiness. Our objective create system that not only optimises of teams scheduled tasks but also provides clear, understandable explanations decisions, particularly in cases where problem infeasible. By incorporating human-in-the-loop...
Los géneros de videojuegos basados en dinámicas multijugador están sostenidos por la dimensión social inherente a estas. Esta contribuye manera evidente su éxito o fracaso y tanto los creadores consideran atentamente durante el diseño previo experiencia.Comparando estas comunidades con las que se dan ámbito educativo encontramos paralelismos estructuras sociales ambos sistemas, lo propicia extrapolación aplicación resultados investigación sobre aulas universitarias.Esta adaptación plantea...
This paper describes a robot trajectory planning method for grasping an object placed on table. In conventional methods, the more obstacles are table, calculation costs needed to find course avoiding obstacles; overcome this problem we use Accumulated Action Data from previous situations. The is composed of arrangement and manipulation manipulator acts information that decided by comparing data with present arrangement. For evaluating method, performed experiments in different conditions simulator.
Machine learning is a discipline with many simulator-driven applications oriented to learn behavior. However, behavior simulation it comes number of associated difficulties, like the lack clear reward function, actions that depend state actor and alternation different policies. We present method for called Contextual Action Multiple Policy Inverse Reinforcement Learning (CAMP-IRL) tackles those factors. Our allows extract multiple functions generates profiles from them. applied our large...