Abstract--We present a two-stage framework that integrates a learning-based estimator and a controller, designed to address contact-intensive tasks. The controller combines a self-supervised and reinforcement learning (RL) approach, strategically dividing the low-level admittance controller's parameters into labelable and non-labelable categories, which are then trained accordingly. To further enhance accuracy and generalization performance, a transformer model is incorporated into the self-supervised learning component. The proposed framework is evaluated on the bolting task using an accurate real-time simulator and successfully transferred to an experimental environment. More visualization results are available on our project website: https://sites.google.com/view/2stagecitt

Abstract--For many robotic manipulation and contact tasks, it is crucial to accurately estimate uncertain object poses, for which certain geometry and sensor information are fused in some optimal fashion. Previous results for this problem primarily adopt sampling-based or end-to-end learning methods, which yet often suffer from the issues of efficiency and generalizability. In this paper, we propose a novel differentiable framework for this uncertain pose estimation during contact, so that it can be solved in an efficient and accurate manner with gradient-based solver. To achieve this, we introduce a new geometric definition that is highly adaptable and capable of providing differentiable contact Figure 1: Graphical abstracts illustrating our differentiable pose estimation features. Then we approach the problem from a bi-level perspective during contact. Left: A peg-in-hole task performed in a hole with and utilize the gradient of these contact features along with pose uncertainty along the x and y directions. Right: Visualization of differentiable optimization to efficiently solve for the uncertain the differentiable cost landscape and the gradient-based optimization pose. Several scenarios are implemented to demonstrate how the process utilizing force/torque sensor information acquired through proposed framework can improve existing methods.

In this paper, we present a new multibody physics simulation framework that utilizes the subsystem-based structure and the Alternating Direction Method of Multiplier (ADMM). The major challenge in simulating complex high degree of freedom systems is a large number of coupled constraints and large-sized matrices. To address this challenge, we first split the multibody into several subsystems and reformulate the dynamics equation into a subsystem perspective based on the structure of their interconnection. Then we utilize ADMM with our novel subsystem-based variable splitting scheme to solve the equation, which allows parallelizable and modular architecture. The resulting algorithm is fast, scalable, versatile, and converges well while maintaining solution consistency. Several illustrative examples are implemented with performance evaluation results showing advantages over other state-of-the-art algorithms.

There is a growing interest in learning a velocity command tracking controller of quadruped robot using reinforcement learning due to its robustness and scalability. However, a single policy, trained end-to-end, usually shows a single gait regardless of the command velocity. This could be a suboptimal solution considering the existence of optimal gait according to the velocity for quadruped animals. In this work, we propose a hierarchical controller for quadruped robot that could generate multiple gaits (i.e. pace, trot, bound) while tracking velocity command. Our controller is composed of two policies, each working as a central pattern generator and local feedback controller, and trained with hierarchical reinforcement learning. Experiment results show 1) the existence of optimal gait for specific velocity range 2) the efficiency of our hierarchical controller compared to a controller composed of a single policy, which usually shows a single gait. Codes are publicly available.

Deep neural networks (DNNs) have become an essential method for solving difficult tasks in computer vision, signal processing, and natural language processing (He et al., 2016; Choi et al., 2018; Han et al., 2017; Van Den Oord et al., 2016; Seo et al., 2016; Vaswani et al., 2017). As the capabilities of deep learning have expanded with more modular architectures and advanced optimization methods, the number of hyperparameters has increased in general. This increase of hyperparameter sizes makes it more difficult for a researcher to optimize a model, wasting a lot of human resources and potentially leading unfair comparisons. This reinforces the importance of efficient automated hyperparameter tuning methods and interfaces. To address this problem, several hyperparameter optimization (HyperOpt) methods have been proposed (Jaderberg et al., 2017; Falkner et al., 2018; Li et al., 2017). These methods have many advantages such as strong final performance, parallelism, early stopping which significantly improve performance in terms of computing resource efficiency and optimization time.