相关论文: AMPLIFY: Actionless Motion Priors for Robot Learni…

Large and diverse datasets have been the cornerstones of many impressive advancements in artificial intelligence. Intelligent creatures, however, learn by interacting with the environment, which changes the input sensory signals and the…

Imitation learning has shown great promise in robotic manipulation, but the policy's execution is often unsatisfactorily slow due to commonly tardy demonstrations collected by human operators. In this work, we present DemoSpeedup, a…

Humans often acquire new skills through observation and imitation. For robotic agents, learning from the plethora of unlabeled video demonstration data available on the Internet necessitates imitating the expert without access to its…

The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly.…

The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical flow estimation has become a research…

We present a unified probabilistic model that learns a representative set of discrete vehicle actions and predicts the probability of each action given a particular scenario. Our model also enables us to estimate the distribution over…

Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid…

Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we…

Ego-centric driving videos available online provide an abundant source of visual data for autonomous driving, yet their lack of annotations makes it difficult to learn representations that capture both semantic structure and 3D geometry.…

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…

The goal of this paper is to self-train a 3D convolutional neural network on an unlabeled video collection for deployment on small-scale video collections. As smaller video datasets benefit more from motion than appearance, we strive to…

Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present…

We introduce $\Psi_0$ (Psi-Zero), an open foundation model to address challenging humanoid loco-manipulation tasks. While existing approaches often attempt to address this fundamental problem by co-training on large and diverse human and…

Learning agile humanoid behaviors from human motion offers a powerful route to natural, coordinated control, but existing approaches face a persistent trade-off: reference-tracking policies are often brittle outside the demonstration…

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct…

Training generalist policies for robotic manipulation has shown great promise, as they enable language-conditioned, multi-task behaviors across diverse scenarios. However, evaluating these policies remains difficult because real-world…

Learning-based methods have improved locomotion skills of quadruped robots through deep reinforcement learning. However, the sim-to-real gap and low sample efficiency still limit the skill transfer. To address this issue, we propose an…

Safe and effective motion planning is crucial for autonomous robots. Diffusion models excel at capturing complex agent interactions, a fundamental aspect of decision-making in dynamic environments. Recent studies have successfully applied…

Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward…

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like…