Related papers: Zero-Shot Sim-to-Real Robot Learning: A Dexterous …

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are also wide researches in…

Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability…

Existing learning approaches to dexterous manipulation use demonstrations or interactions with the environment to train black-box neural networks that provide little control over how the robot learns the skills or how it would perform post…

Learning a generalist control policy for dexterous manipulation typically relies on large-scale datasets. Given the high cost of real-world data collection, a practical alternative is to generate synthetic data through simulation. However,…

We study reinforcement learning (RL) in settings where observations are high-dimensional, but where an RL agent has access to abstract knowledge about the structure of the state space, as is the case, for example, when a robot is tasked to…

Imitation learning methods need significant human supervision to learn policies robust to changes in object poses, physical disturbances, and visual distractors. Reinforcement learning, on the other hand, can explore the environment…

We present CREST, an approach for causal reasoning in simulation to learn the relevant state space for a robot manipulation policy. Our approach conducts interventions using internal models, which are simulations with approximate dynamics…

Zero-shot learning methods typically assume that the new, unseen classes encountered during deployment come from the same distribution as the the classes in the training set. However, real-world scenarios often involve class distribution…

Deep learning-based robotic grasping has made significant progress thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often trained on as few as hundreds or thousands of unique object…

Dynamic state representation learning is an important task in robot learning. Latent space that can capture dynamics related information has wide application in areas such as accelerating model free reinforcement learning, closing the…

Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer across different robotic platforms, focusing on peg-in-hole task…

Bayesian policy reuse (BPR) is a general policy transfer framework for selecting a source policy from an offline library by inferring the task belief based on some observation signals and a trained observation model. In this paper, we…

Learning-based approaches, particularly reinforcement learning (RL), have become widely used for developing control policies for autonomous agents, such as locomotion policies for legged robots. RL training typically maximizes a predefined…

Domain randomization (DR) is widely used in policy learning to improve robustness to modeling error, but remains underexplored in contact-rich sampling-based predictive control (SPC), where rollout quality is highly sensitive to…

Autonomous visual navigation is an essential element in robot autonomy. Reinforcement learning (RL) offers a promising policy training paradigm. However existing RL methods suffer from high sample complexity, poor sim-to-real transfer, and…

Domain randomization is a simple, effective, and flexible scheme for obtaining robust feedback policies aimed at reducing the sim-to-real gap due to model mismatch. While domain randomization methods have yielded impressive demonstrations…

Object handover is an important skill that we use daily when interacting with other humans. To deploy robots in collaborative setting, like houses, being able to receive and handing over objects safely and efficiently becomes a crucial…

Robot simulation has been an essential tool for data-driven manipulation tasks. However, most existing simulation frameworks lack either efficient and accurate models of physical interactions with tactile sensors or realistic tactile…

Many state-of-the art robotic applications utilize series elastic actuators (SEAs) with closed-loop force control to achieve complex tasks such as walking, lifting, and manipulation. Model-free PID control methods are more prone to…

The problem of uncertainty is a feature of real world robotics problems and any control framework must contend with it in order to succeed in real applications tasks. Reinforcement Learning is no different, and epistemic uncertainty arising…