The scarcity of diverse and high-quality data impedes the quest to build a generalist robotic system. Current robotics data collection efforts face many challenges: the need for physical robotic hardware, setting up the environment, frequent resets, and the fatigue for data collectors operating real robots. We introduce DART, a teleoperation platform designed for crowdsourcing that reimagines robotic data collection by leveraging cloud-based simulation and augmented reality (AR) to address many limitations of prior data collection efforts. User studies show that DART enables higher data collection throughput and lower physical fatigue than real-world teleoperation. We also demonstrate that policies trained using DART-collected datasets successfully transfer to reality and are robust to unseen visual disturbances. All data collected through DART is automatically stored in a cloud-hosted database, DexHub, paving the path for an ever-growing data hub for robot learning. https://dexhub.ai/project

Many roboticists dream of presenting a robot with a task in the evening and returning the next morning to find the robot capable of solving the task. What is preventing us from achieving this? Sim-to-real reinforcement learning (RL) has achieved impressive performance on challenging robotics tasks, but requires substantial human effort to set up the task in a way that is amenable to RL. It's our position that algorithmic improvements in policy optimization and other ideas should be guided towards resolving the primary bottleneck of shaping the training environment, i.e., designing observations, actions, rewards and simulation dynamics. Most practitioners don't tune the RL algorithm, but other environment parameters to obtain a desirable controller. We posit that scaling RL to diverse robotic tasks will only be achieved if the community focuses on automating environment shaping procedures.

Programming manipulation behaviors can become increasingly difficult with a growing number and complexity of manipulation tasks, particularly in a dynamic and unstructured environment. Recent progress in unsupervised skill discovery algorithms has shown great promise in learning an extensive collection of behaviors without extrinsic supervision. On the other hand, safety is one of the most critical factors for real- world robot applications. As skill discovery methods typically encourage exploratory and dynamic behaviors, it can often be the case that a large portion of learned skills remain too dangerous and unsafe. In this paper, we introduce the novel problem of Safety-Aware Skill Discovery, which aims to learn, in a task-agnostic fashion, a repertoire of reusable skills that are inherently safe to be composed for solving downstream tasks. We present a computationally tractable algorithm that learns a latent-conditioned skill policy that maximizes intrinsic rewards regularized with a safety-critic that can model any user-defined safety constraints. Using the pretrained safe skill repertoire, hierarchical reinforcement learning can solve multiple downstream tasks without the need for explicit consideration of safety during training and testing. We evaluate our algorithm on a collection of force-controlled robotic manipulation tasks in simulation and show promising downstream task performance while satisfying safety constraints.

Robotic painting tasks in the real world are often made complicated by the highly complex and stochastic nature of the dynamics that underlie, e.g., physical contact between the painting tool and a canvas, color blendings between painting mediums, and many more. Simulation-based inverse graphics algorithms, for example, can not be directly transferred to the real-world due in large to the considerable gap in the viable range of painting strokes the robot can accurately generate onto the physical canvas. In this paper, we aim at minimizing this gap by appealing to a data-driven skill learning approach. The core idea lies in allowing the robot to learn continuous stroke-level skills that jointly encodes action trajectories and painted outcomes from an extensive collection of human demonstrations. We demonstrate the efficacy of our method through extensive real-world experiments using a 4-dof torque-controllable manipulator with a digital canvas(iPad).