Zobrazeno 1 - 10
of 59
pro vyhledávání: '"Tonneau, Steve"'
Publikováno v:
2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)
Humans can exploit contacts anywhere on their body surface to manipulate large and heavy items, objects normally out of reach or multiple objects at once. However, such manipulation through contacts using the whole surface of the body remains extreme
Externí odkaz:
http://arxiv.org/abs/2408.15726
Autor:
Wang, Jiayi, Samadi, Saeid, Wang, Hefan, Fernbach, Pierre, Stasse, Olivier, Vijayakumar, Sethu, Tonneau, Steve
How many ways are there to climb a staircase in a given number of steps? Infinitely many, if we focus on the continuous aspect of the problem. A finite, possibly large number if we consider the discrete aspect, \emph{i.e.} on which surface which effe
Externí odkaz:
http://arxiv.org/abs/2407.12962
Autor:
Wang, Jiayi, Kim, Sanghyun, Lembono, Teguh Santoso, Du, Wenqian, Shim, Jaehyun, Samadi, Saeid, Wang, Ke, Ivan, Vladimir, Calinon, Sylvain, Vijayakumar, Sethu, Tonneau, Steve
Planning multi-contact motions in a receding horizon fashion requires a value function to guide the planning with respect to the future, e.g., building momentum to traverse large obstacles. Traditionally, the value function is approximated by computi
Externí odkaz:
http://arxiv.org/abs/2306.04732
Despite impressive results, reinforcement learning (RL) suffers from slow convergence and requires a large variety of tuning strategies. In this paper, we investigate the ability of RL algorithms on simple continuous control tasks. We show that witho
Externí odkaz:
http://arxiv.org/abs/2305.15244
Autor:
Corbères, Thomas, Mastalli, Carlos, Merkt, Wolfgang, Havoutis, Ioannis, Fallon, Maurice, Mansard, Nicolas, Flayols, Thomas, Vijayakumar, Sethu, Tonneau, Steve
Real-time synthesis of legged locomotion maneuvers in challenging industrial settings is still an open problem, requiring simultaneous determination of footsteps locations several steps ahead while generating whole-body motions close to the robot's l
Externí odkaz:
http://arxiv.org/abs/2305.08926
Autor:
Shim, Jaehyun, Mastalli, Carlos, Corbères, Thomas, Tonneau, Steve, Ivan, Vladimir, Vijayakumar, Sethu
Publikováno v:
IEEE International Conference on Robotics and Automation (ICRA), 2023
State-of-the-art approaches to footstep planning assume reduced-order dynamics when solving the combinatorial problem of selecting contact surfaces in real time. However, in exchange for computational efficiency, these approaches ignore joint torque
Externí odkaz:
http://arxiv.org/abs/2303.13726
Autor:
Mastalli, Carlos, Chhatoi, Saroj Prasad, Corbères, Thomas, Tonneau, Steve, Vijayakumar, Sethu
Publikováno v:
IEEE Transactions on Robotics, 2023
Optimal control (OC) using inverse dynamics provides numerical benefits such as coarse optimization, cheaper computation of derivatives, and a high convergence rate. However, to take advantage of these benefits in model predictive control (MPC) for l
Externí odkaz:
http://arxiv.org/abs/2209.05375
Robot design optimization, imitation learning and system identification share a common problem which requires optimization over robot or task parameters at the same time as optimizing the robot motion. To solve these problems, we can use differentiab
Externí odkaz:
http://arxiv.org/abs/2209.01117
Derivative based optimization methods are efficient at solving optimal control problems near local optima. However, their ability to converge halts when derivative information vanishes. The inference approach to optimal control does not have strict r
Externí odkaz:
http://arxiv.org/abs/2109.11361
Autor:
Tonneau, Steve
Non-linear Trajectory Optimisation (TO) methods require good initial guesses to converge to a locally optimal solution. A feasible guess can often be obtained by allocating a large amount of time for the trajectory to complete. However for unstable d
Externí odkaz:
http://arxiv.org/abs/2109.07977