Related papers: KITE: Keypoint-Conditioned Policies for Semantic M…
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four…
Visual imitation learning provides efficient and intuitive solutions for robotic systems to acquire novel manipulation skills. However, simultaneously learning geometric task constraints and control policies from visual inputs alone remains…
We propose a sign language translation system based on human keypoint estimation. It is well-known that many problems in the field of computer vision require a massive amount of dataset to train deep neural network models. The situation is…
Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…
While imitation learning has shown impressive results in single-task robot manipulation, scaling it to multi-task settings remains a fundamental challenge due to issues such as suboptimal demonstrations, trajectory noise, and behavioral…
Self-improvement requires robotic systems to initially learn from human-provided data and then gradually enhance their capabilities through interaction with the environment. This is similar to how humans improve their skills through…
Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they…
The speed and accuracy with which robots are able to interpret natural language is fundamental to realizing effective human-robot interaction. A great deal of attention has been paid to developing models and approximate inference algorithms…
Humans are capable of completing a range of challenging manipulation tasks that require reasoning jointly over modalities such as vision, touch, and sound. Moreover, many such tasks are partially-observed; for example, taking a notebook out…
When instructing robots, users want to flexibly express constraints, refer to arbitrary landmarks, and verify robot behavior, while robots must disambiguate instructions into specifications and ground instruction referents in the real…
Task specification for robotic manipulation in open-world environments is challenging, requiring flexible and adaptive objectives that align with human intentions and can evolve through iterative feedback. We introduce Iterative Keypoint…
Imitation learning techniques have been shown to be highly effective in real-world control scenarios, such as robotics. However, these approaches not only suffer from compounding error issues but also require human experts to provide…
It is highly desirable for robots that work alongside humans to be able to understand instructions in natural language. Existing language conditioned imitation learning models directly predict the actuator commands from the image…
Humanoid robots are well suited for human habitats due to their morphological similarity, but developing controllers for them is a challenging task that involves multiple sub-problems, such as control, planning and perception. In this…
Comprehension of spoken natural language is an essential component for robots to communicate with human effectively. However, handling unconstrained spoken instructions is challenging due to (1) complex structures including a wide variety…
Online Imitation Learning struggles with the gap between extensive online exploration space and limited expert trajectories, hindering efficient exploration due to inaccurate reward estimation. Inspired by the findings from cognitive…
Embodied Instruction Following (EIF) requires agents to complete human instruction by interacting objects in complicated surrounding environments. Conventional methods directly consider the sparse human instruction to generate action plans…
Robotic tasks such as planning and navigation require a hierarchical semantic understanding of a scene, which could include multiple floors and rooms. Current methods primarily focus on object segmentation for 3D scene understanding.…
Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent…
We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual…