相关论文: Hierarchical visuomotor control of humanoids
Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, existing approaches rely on heavily pre-processed human-to-humanoid motion retargeting and position-only…
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…
We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects. This problem presents a number of…
Contact-rich manipulation has become increasingly important in robot learning. However, previous studies on robot learning datasets have focused on rigid objects and underrepresented the diversity of pressure conditions for real-world…
Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the…
Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements accordingly. Behaviors like searching for objects, reaching,…
Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects.…
Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated…
Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is…
We present a hierarchical policy-learning framework that enables a legged humanoid to cooperatively carry extended loads with a human partner using only haptic cues for intent inference. At the upper tier, a lightweight behavior-cloning…
Humans' ability to smoothly switch between locomotion and manipulation is a remarkable feature of sensorimotor coordination. Leaning and replication of such human-like strategies can lead to the development of more sophisticated robots…
Human-robot collaborative tasks foresee interactions between humans and robots with various degrees of complexity. Specifically, for tasks which involve physical contact among the agents, challenges arise in the modelling and control of…
Legged robots have significant potential to operate in highly unstructured environments. The design of locomotion control is, however, still challenging. Currently, controllers must be either manually designed for specific robots and tasks,…
Learning versatile whole-body skills by tracking various human motions is a fundamental step toward general-purpose humanoid robots. This task is particularly challenging because a single policy must master a broad repertoire of motion…
Many of today's robot perception systems aim at accomplishing perception tasks that are too simplistic and too hard. They are too simplistic because they do not require the perception systems to provide all the information needed to…
Modeling and control of the human musculoskeletal system is important for understanding human motor functions, developing embodied intelligence, and optimizing human-robot interaction systems. However, current human musculoskeletal models…
Visuomotor control (VMC) is an effective means of achieving basic manipulation tasks such as pushing or pick-and-place from raw images. Conditioning VMC on desired goal states is a promising way of achieving versatile skill primitives.…
Legged robots navigating crowded scenes and complex terrains in the real world are required to execute dynamic leg movements while processing visual input for obstacle avoidance and path planning. We show that a quadruped robot can acquire…
With recent advancements in AI and computational tools, intelligent paradigms have emerged to enhance fields like shared autonomy and human-machine teaming in healthcare. Advanced AI algorithms (e.g., reinforcement learning) can…