Jingyun Yang

We propose novel metrics, tasks, visualization tools and methods for “policy mobilization,” the problem of taking a non-mobile manipulation policy and finding a proper initial robot pose from which to execute it on a mobile platform.

We present CUPID, a robot data curation algorithm that leverages influence functions to predictively answer counterfactual questions about the effect of each demonstration on downstream policy performance.

We introduce HoMeR (Hybrid Whole-Body Policies for Mobile Robots), which combines a hybrid IL agent with a fast, kinematics-based whole-body controller for sample-efficient, generalizable mobile manipulation in-the-wild.

We propose EquiBot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. In the real world, with 10 variations of 6 mobile manipulation tasks, we show that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.

We propose Sentinel, a runtime monitoring framework that splits the detection of failures into two complementary categories: 1) Erratic failures, which we detect using statistical measures of temporal action consistency, and 2) task progression failures, where we use Vision Language Models (VLMs) to detect when the policy confidently and consistently takes actions that do not solve the task.

We introduce DROID (Distributed Robot Interaction Dataset), a diverse robot manipulation dataset with 76k demonstration trajectories or 350h of interaction data, collected across 564 scenes and 86 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months.

We introduce the Open X-Embodiment Dataset, the largest open-source real robot dataset to date. It contains 1M+ real robot trajectories spanning 22 robot embodiments, from single robot arms to bi-manual robots and quadrupeds.

We propose a method that utilizes SIM(3)-equivariant network structures that guarantee generalization across all possible object translations, rotations, and scales by construction. Our method can successfully generalize from a small set of human demonstrations in table-top setups to diverse target scenarios in challenging real world manipulation tasks involving deformable and articulated objects.

We propose a system that enables autonomous and efficient real-world robot learning. Our insights are to utilize calibrated offline RL techniques to ensure efficient online fine-tuning of a pre-trained policy in the presence of distribution shifts and leverage pre-trained vision language models (VLMs) to build a robust reward classifier for autonomously providing reward signals during the online fine-tuning process.

We study the challenges that differentiable simulation presents when it is not feasible to expect that a single descent reaches a global optimum, which is often a problem in contact-rich scenarios. In dynamic environments, we find that differentiable simulators produce rugged landscapes with nonetheless useful gradients in some parts of the space. We propose a method that combines Bayesian optimization with semi-local “leaps” to obtain a global search method that can use gradients effectively, while also maintaining robust performance in regions with noisy gradients.

We develop a method for learning periodic tasks from visual demonstrations. The core idea is to leverage periodicity in the policy structure to model periodic aspects of the tasks. We use active learning to optimize parameters of rhythmic dynamic movement primitives (rDMPs) and propose an objective to maximize the similarity between the motion of objects manipulated by the robot and the desired motion in human video demonstrations.

We propose a method for manipulating diverse objects across a wide range of initial and goal configurations and camera placements. We disentangle the standard image-to-action mapping into two separate modules: (1) a behavior selector which conditions on intrinsic and semantically-rich object appearance features to select the behaviors that can successfully perform the desired tasks on the object in hand, and (2) a library of behaviors each of which conditions on extrinsic and abstract object properties to predict actions to execute over time.

Autonomous agents with multiple end-effectors can perform complex tasks by coordinating sub-skills of each end-effector. To realize temporal and behavioral coordination of skills, we propose a hierarchical framework that first individually trains sub-skills of each end-effector with skill behavior diversification, and learns to coordinate end-effectors using diverse behaviors of the skills.

To flexibly and efficiently reason about temporal sequences, abstract representations that compactly represent the important information in the sequence are needed. We propose to construct such representations using a hierarchical Keyframe‐Inpainter (KeyIn) model that first generates keyframes and their temporal placement and then inpaints the sequences between keyframes. We propose a fully differentiable formulation for efficiently learning the keyframe placement. We show that KeyIn finds informative keyframes in several datasets with diverse dynamics. When evaluated on a planning task, KeyIn outperforms other recent proposals for learning hierarchical representations.