Goto

Collaborating Authors

AI researchers test a robot's dexterity by handing it a Rubik's cube

#artificialintelligence

Humans can manipulate Rubik's cubes with relative ease, but robots have historically had a tougher go of it. That's not to suggest there aren't exceptions to the rule -- an MIT invention recently solved a cube in a record-breaking 0.38 seconds -- but they typically involve purpose-built motors and controls. Encouragingly, a group of researchers at Tencent and the Chinese University of Hong Kong say they've designed a Rubik's cube manipulator that uses multi-fingered hands. "Dexterous in-hand manipulation is a key building block for robots to achieve human-level dexterity, and accomplish everyday tasks which involve rich contact," wrote the researchers. "Despite concerted progress, reliable multi-fingered dexterous hand manipulation has remained an open challenge, due to its complex contact patterns, high dimensional action space, and fragile mechanical structure."


This five-fingered robot hand learns to get a grip on its own

#artificialintelligence

Robots today can perform space missions, solve a Rubik's cube, sort hospital medication and even make pancakes. But most can't manage the simple act of grasping a pencil and spinning it around to get a solid grip. Intricate tasks that require dexterous in-hand manipulation--rolling, pivoting, bending, sensing friction and other things humans do effortlessly with our hands--have proved notoriously difficult for robots. Now, a University of Washington team of computer science and engineering researchers has built a robot hand that can not only perform dexterous manipulation but also learn from its own experience without needing humans to direct it. Their latest results are detailed in a paper to be presented May 17 at the IEEE International Conference on Robotics and Automation.


Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost

arXiv.org Artificial Intelligence

Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators. However, such hands pose a major challenge for autonomous control, due to the high dimensionality of their configuration space and complex intermittent contact interactions. In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands. Deep RL provides an end-to-end approach to directly map sensor readings to actions, without the need for task specific models or policy classes. We show that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation. We learn a variety of complex behaviors on two different low-cost hardware platforms. We show that each task can be learned entirely from scratch, and further study how the learning process can be further accelerated by using a small number of human demonstrations to bootstrap learning. Our experiments demonstrate that complex multi-fingered manipulation skills can be learned in the real world in about 4-7 hours for most tasks, and that demonstrations can decrease this to 2-3 hours, indicating that direct deep RL training in the real world is a viable and practical alternative to simulation and model-based control. \url{https://sites.google.com/view/deeprl-handmanipulation}


Solving Rubik's Cube with a Robot Hand

arXiv.org Artificial Intelligence

We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key components: a novel algorithm, which we call automatic domain randomization (ADR) and a robot platform built for machine learning. ADR automatically generates a distribution over randomized environments of ever-increasing difficulty. Control policies and vision state estimators trained with ADR exhibit vastly improved sim2real transfer. For control policies, memory-augmented models trained on an ADR-generated distribution of environments show clear signs of emergent meta-learning at test time. The combination of ADR with our custom robot platform allows us to solve a Rubik's cube with a humanoid robot hand, which involves both control and state estimation problems. Videos summarizing our results are available: https://openai.com/blog/solving-rubiks-cube/


Deep Dynamics Models for Dexterous Manipulation

#artificialintelligence

Figure 1: Our approach (PDDM) can efficiently and effectively learn complex dexterous manipulation skills in both simulation and the real world. Here, the learned model is able to control the 24-DoF Shadow Hand to rotate two free-floating Baoding balls in the palm, using just 4 hours of real-world data with no prior knowledge/assumptions of system or environment dynamics. Dexterous manipulation with multi-fingered hands is a grand challenge in robotics: the versatility of the human hand is as yet unrivaled by the capabilities of robotic systems, and bridging this gap will enable more general and capable robots. Although some real-world tasks (like picking up a television remote or a screwdriver) can be accomplished with simple parallel jaw grippers, there are countless tasks (like functionally using the remote to change the channel or using the screwdriver to screw in a nail) in which dexterity enabled by redundant degrees of freedom is critical. In fact, dexterous manipulation is defined as being object-centric, with the goal of controlling object movement through precise control of forces and motions -- something that is not possible without the ability to simultaneously impact the object from multiple directions.