Related papers: Towards Online Learning from Corrective Demonstrat…
The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large…
Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…
For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which…
When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop…
Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…
Learning from Demonstration (LfD) offers a promising paradigm for robot skill acquisition. Recent approaches attempt to extract manipulation commands directly from video demonstrations, yet face two critical challenges: (1) general video…
Machine learning, artificial intelligence and especially deep learning based approaches are often used to simplify or eliminate the burden of programming industrial robots. Using these approaches robots inherently learn a skill instead of…
As environments involving both robots and humans become increasingly common, so does the need to account for people during planning. To plan effectively, robots must be able to respond to and sometimes influence what humans do. This…
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be…
Supplementary Training on Intermediate Labeled-data Tasks (STILTs) is a widely applied technique, which first fine-tunes the pretrained language models on an intermediate task before on the target task of interest. While STILTs is able to…
Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots.…
This paper presents an overview of robot failure detection work from HRI and adjacent fields using failures as an opportunity to examine robot explanation behaviours. As humanoid robots remain experimental tools in the early 2020s,…
Industrial robots play an increasingly important role in a growing number of fields. For example, robotics is used to increase productivity while reducing costs in various aspects of manufacturing. Since robots are often set up in…
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…
Robotic systems have become integral to smart environments, enabling applications ranging from urban surveillance and automated agriculture to industrial automation. However, their effective operation in dynamic settings - such as smart…
Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task…
We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by 1) task-relevant autonomy, which guides exploration towards…
Machine learning models are essential tools in various domains, but their performance can degrade over time due to changes in data distribution or other factors. On one hand, detecting and addressing such degradations is crucial for…
The statistical machine learning community has demonstrated considerable resourcefulness over the years in developing highly expressive tools for estimation, prediction, and inference. The bedrock assumptions underlying these developments…
Robots learning a new manipulation task from a small amount of demonstrations are increasingly demanded in different workspaces. A classifier model assessing the quality of actions can predict the successful completion of a task, which can…