相关论文: Reinforcement Learning of Active Vision for Manipu…

In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots.…

When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit…

Language-guided active sensing is a robotics subtask where a robot with an onboard sensor interacts efficiently with the environment via object manipulation to maximize perceptual information, following given language instructions. These…

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

Manipulating objects without grasping them is an essential component of human dexterity, referred to as non-prehensile manipulation. Non-prehensile manipulation may enable more complex interactions with the objects, but also presents…

We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to…

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

Articulated object manipulation is a challenging task, requiring constrained motion and adaptive control to handle the unknown dynamics of the manipulated objects. While reinforcement learning (RL) has been widely employed to tackle various…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

We examine the problem of joint top-down active search of multiple objects under interaction, e.g., person riding a bicycle, cups held by the table, etc.. Such objects under interaction often can provide contextual cues to each other to…

In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of…

Estimating the pose and shape of hands and objects under interaction finds numerous applications including augmented and virtual reality. Existing approaches for hand and object reconstruction require explicitly defined physical constraints…

Large-scale real-world robot data collection is a prerequisite for bringing robots into everyday deployment. However, existing pipelines often rely on specialized handheld devices to bridge the embodiment gap, which not only increases…

We describe a learning-based approach to hand-eye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the probability that…

Robotic dexterous manipulation is a challenging problem due to high degrees of freedom (DoFs) and complex contacts of multi-fingered robotic hands. Many existing deep reinforcement learning (DRL) based methods aim at improving sample…

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we…

Joint attention - the ability to purposefully coordinate attention with another agent, and mutually attend to the same thing -- is a critical component of human social cognition. In this paper, we ask whether joint attention can be useful…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where an apt agent Bob acts independently, with non-observable…