We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …
Modeling a generalized visuomotor policy has been a longstanding challenge for both computer vision and robotics communities. Existing approaches often fail to efficiently …
Representation learning approaches for robotic manipulation have boomed in recent years. Due to the scarcity of in-domain robot data, prevailing methodologies tend to leverage large …
3D perceptual representations are well suited for robot manipulation as they easily encode occlusions and simplify spatial reasoning. Many manipulation tasks require high spatial …
A Ma, G Chi, S Ivaldi, L Chen - Complex & Intelligent Systems, 2024 - Springer
Learning visual predictive models has great potential for real-world robot manipulations. Visual predictive models serve as a model of real-world dynamics to comprehend the …
Autonomous robotic systems capable of learning novel manipulation tasks are poised to transform industries from manufacturing to service automation. However, modern methods …
X Zhang, Y Liu, H Chang, A Boularias - arXiv preprint arXiv:2406.07837, 2024 - arxiv.org
Learning general-purpose models from diverse datasets has achieved great success in machine learning. In robotics, however, existing methods in multi-task learning are typically …
S Kumra, S Joshi, F Sahin - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
In this work, we focus on multi-step manipulation tasks that involve long-horizon planning and considers progress reversal. Such tasks interlace high-level reasoning that consists of …
We propose a novel framework for learning high-level cognitive capabilities in robot manipulation tasks, such as making a smiley face using building blocks. These tasks often …