Related papers: Mitigating the Human-Robot Domain Discrepancy in V…
Data-driven techniques for machine vision heavily depend on the training data to sufficiently resemble the data occurring during test and application. However, in practice unknown distortion can lead to a domain gap between training and…
We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen objects using the grasp distribution learned from the training set,…
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models…
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated…
Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these…
Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…
Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system,…
Mimicry is a fundamental learning mechanism in humans, enabling individuals to learn new tasks by observing and imitating experts. However, applying this ability to robots presents significant challenges due to the inherent differences…
Recently, much progress has been made for self-supervised action recognition. Most existing approaches emphasize the contrastive relations among videos, including appearance and motion consistency. However, two main issues remain for…
Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information…
Pedestrian motion, due to its causal nature, is strongly influenced by domain gaps arising from discrepancies between training and testing data distributions. Focusing on 3D human pose estimation, this work presents a controllable human…
Finding an efficient way to adapt robot trajectory is a priority to improve overall performance of robots. One approach for trajectory planning is through transferring human-like skills to robots by Learning from Demonstrations (LfD). The…
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…
When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…
Conventional robots possess a limited understanding of their kinematics and are confined to preprogrammed tasks, hindering their ability to leverage tools efficiently. Driven by the essential components of tool usage - grasping the desired…
Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in…
The dominant paradigm for end-to-end robot learning focuses on optimizing task-specific objectives that solve a single robotic problem such as picking up an object or reaching a target position. However, recent work on high-capacity models…
The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…
This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…
In this work, we focus on text-based person retrieval, which identifies individuals based on textual descriptions. Despite advancements enabled by synthetic data for pretraining, a significant domain gap, due to variations in lighting,…