Related papers: Generalization in Dexterous Manipulation via Geome…

Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the…

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D…

In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies without prior knowledge of the dynamics of the…

Training agents to autonomously learn how to use anthropomorphic robotic hands has the potential to lead to systems capable of performing a multitude of complex manipulation tasks in unstructured and uncertain environments. In this work, we…

Human hands possess the dexterity to interact with diverse objects such as grasping specific parts of the objects and/or approaching them from desired directions. More importantly, humans can grasp objects of any shape without…

In recent years, policy learning methods using either reinforcement or imitation have made significant progress. However, both techniques still suffer from being computationally expensive and requiring large amounts of training data. This…

Functional grasping with dexterous robotic hands is a key capability for enabling tool use and complex manipulation, yet progress has been constrained by two persistent bottlenecks: the scarcity of large-scale datasets and the absence of…

Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the…

We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs…

We consider task allocation for multi-object transport using a multi-robot system, in which each robot selects one object among multiple objects with different and unknown weights. The existing centralized methods assume the number of…

For contact-intensive tasks, the ability to generate policies that produce comprehensive tactile-aware motions is essential. However, existing data collection and skill learning systems for dexterous manipulation often suffer from…

Picking cluttered general objects is a challenging task due to the complex geometries and various stacking configurations. Many prior works utilize pose estimation for picking, but pose estimation is difficult on cluttered objects. In this…

Robotics policies are always subjected to complex, second order dynamics that entangle their actions with resulting states. In reinforcement learning (RL) contexts, policies have the burden of deciphering these complicated interactions over…

Learning robotic manipulation skills from vision is a promising approach for developing robotics applications that can generalize broadly to real-world scenarios. As such, many approaches to enable this vision have been explored with…

Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations,…

Large, general-purpose robotic policies trained on diverse demonstration datasets have been shown to be remarkably effective both for controlling a variety of robots in a range of different scenes, and for acquiring broad repertoires of…

Deep reinforcement learning has shown its advantages in real-time decision-making based on the state of the agent. In this stage, we solved the task of using a real robot to manipulate the cube to a given trajectory. The task is broken down…

The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations. This inductive bias can be injected into neural…

Using tactile sensors for manipulation remains one of the most challenging problems in robotics. At the heart of these challenges is generalization: How can we train a tactile-based policy that can manipulate unseen and diverse objects? In…

The use of multi-camera views simultaneously has been shown to improve the generalization capabilities and performance of visual policies. However, the hardware cost and design constraints in real-world scenarios can potentially make it…