Thus, it is We can make very skillful use of various contacts desirable that a planning algorithm be robust to various (e.g., with the environment, our own body, etc.) to perform uncertainties like grasp center, extrinsic contact location, etc. complex manipulation. In a striking contrast, achieving such We present a method which can incorporate uncertainties in dexterous behavior for robots remains very challenging. Using several of the kinematic constraints to generate robust plans environmental contacts efficiently can provide additional for perform in-hand manipulation. This idea is also illustrated dexterity to robots while performing complex manipulation in Figure 1, where a naïve plan can easily lose contact with the [1]. However, the current generation of robotic systems environment due to uncertainty in the grasp location or the mostly avoid making contacts with their environment.

To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowledge of how to perform a task with a robot through multi-modal instructions in their demonstrations, showing a sequence of short-horizon steps to achieve a long-horizon goal. This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement primitives (DMPs) and (2) style-transfer-based training that employs multi-task learning with video captioning and weakly-supervised learning with a semantic classifier to exploit unpaired video-action data. We built a system that accomplishes various cooking actions, where an arm robot executes a DMP sequence acquired from a cooking video using the audio-visual Transformer. Experiments with Epic-Kitchen-100, YouCookII, QuerYD, and in-house instruction video datasets show that the proposed method improves the quality of DMP sequences by 2.3 times the METEOR score obtained with a baseline video-to-action Transformer. The model achieved 32% of the task success rate with the task knowledge of the object.

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art performance when used in reinforcement learning across a wide range of tasks. However, the algorithm suffers from a number of drawbacks including: lack of stepsize selection criterion, and slow convergence. We investigate the use of a trust region method using dogleg step and a Quasi-Newton approximation for the Hessian for policy optimization. We demonstrate through numerical experiments over a wide range of challenging continuous control tasks that our particular choice is efficient in terms of number of samples and improves performance

This paper presents a problem of model learning to navigate a ball to a goal state in a circular maze environment with two degrees of freedom. Motion of the ball in the maze environment is influenced by several non-linear effects such as friction and contacts, which are difficult to model. We propose a hybrid model to estimate the dynamics of the ball in the maze based on Gaussian Process Regression equipped with basis functions obtained from physic first principles. The accuracy of the hybrid model is compared with standard algorithms for model learning to highlight its efficacy. The learned model is then used to design trajectories for the ball using a trajectory optimization algorithm. We also hope that the system presented in the paper can be used as a benchmark problem for reinforcement and robot learning for its interesting and challenging dynamics and its ease of reproducibility.

Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved, is that the amount of time a robot is occupied learning a task---rather than being productive---can be reduced by transferring the learned task to the real robot. Transfer learning requires some amount of fine-tuning on the real robot. For tasks which involve complex (non-linear) dynamics, the fine-tuning itself may take a substantial amount of time. In order to reduce the amount of fine-tuning we propose to learn robustified controllers in simulation. Robustified controllers are learned by exploiting the ability to change simulation parameters (both appearance and dynamics) for successive training episodes. An additional benefit for this approach is that it alleviates the precise determination of physics parameters for the simulator, which is a non-trivial task. We demonstrate our proposed approach on a real setup in which a robot aims to solve a maze puzzle, which involves complex dynamics due to static friction and potentially large accelerations. We show that the amount of fine-tuning in transfer learning for a robustified controller is substantially reduced compared to a non-robustified controller.