Constrained Exploration and Recovery from Experience Shaping

T.-H. Pham, G. De Magistris, D. J. Agravante, S. Chaudhury, A. Munawar, R. Tachibana, arXiv preprint arXiv:1809.08925

We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding undesirable actions or states, associated to lower rewards, or penalties. The construction and balancing of... [Read More]
Tags: research

Experimental force-torque dataset for robot learning of multi-shape insertion

G. De Magistris, A. Munawar, T.-H. Pham, T. Inoue, P. Vinayavekhin, R. Tachibana, 36th Annual Conference of the Robotics Society of Japan (RSJ), 2018

The accurate modeling of real-world systems and physical interactions is a common challenge towards the resolution of robotics tasks. Machine learning approaches have demonstrated significant results in the modeling of complex systems (e.g., articulated robot structures, cable stretch, fluid dynamics), or to learn robotics tasks (e.g., grasping, reaching) from raw... [Read More]
Tags: research

OptLayer - practical constrained optimization for deep reinforcement learning in the real world

T.-H. Pham, G. De Magistris, R. Tachibana, IEEE International Conference on Robotics and Automation (ICRA), 2018

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real world can have undesirable consequences for the robot or its environment. To overcome such limitations,... [Read More]
Tags: research

MaestROB: a robotics framework for integrated orchestration of low-level control and high-level reasoning

A. Munawar, G. De Magistris, T.-H. Pham, D. Kimura, M. Tatsubori, T. Moriyama, R. Tachibana, G. Booch, IEEE International Conference on Robotics and Automation (ICRA), 2018

This paper describes a framework called MaestROB. It is designed to make the robots perform complex tasks with high precision by simple high-level instructions given by natural language or demonstration. To realize this, it handles a hierarchical structure by using the knowledge stored in the forms of ontology and rules... [Read More]
Tags: research

Hand-object contact force estimation from markerless visual tracking

T.-H. Pham, N. Kyriazis, A. A. Argyros, A. Kheddar, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017

We consider the problem of estimating realistic contact forces during manipulation, backed with ground-truth measurements, using vision alone. Interaction forces are usually measured by mounting force transducers onto the manipulated objects or the hands. Those are costly, cumbersome, and alter the objects’ physical properties and their perception by the human... [Read More]
Tags: research