Related papers: Compositional Multi-Object Reinforcement Learning …
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…
Learned visuomotor policies have shown considerable success as an alternative to traditional, hand-crafted frameworks for robotic manipulation. Surprisingly, an extension of these methods to the multiview domain is relatively unexplored. A…
Close and precise placement of irregularly shaped objects requires a skilled robotic system. The manipulation of objects that have sensitive top surfaces and a fixed set of neighbors is particularly challenging. To avoid damaging the…
Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…
Manipulation of deformable objects is a challenging task for a robot. It will be problematic to use a single sensory input to track the behaviour of such objects: vision can be subjected to occlusions, whereas tactile inputs cannot capture…
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a…
Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the…
Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages. We consider multilingual entity linking, where a single model is trained to link references…
In order to deploy autonomous agents in digital interactive environments, they must be able to act robustly in unseen situations. The standard machine learning approach is to include as much variation as possible into training these agents.…
Language-enabled robots have been widely studied over the past years to enable natural human-robot interaction and teaming in various real-world applications. Language-enabled robots must be able to comprehend referring expressions to…
Zero-shot learning has received increasing interest as a means to alleviate the often prohibitive expense of annotating training data for large scale recognition problems. These methods have achieved great success via learning intermediate…
We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining. The…
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…
Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic…
Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential…
Physics-based manipulation in clutter involves complex interaction between multiple objects. In this paper, we consider the problem of learning, from interaction in a physics simulator, manipulation skills to solve this multi-step…
Human-object interaction (HOI) detection is an important part of understanding human activities and visual scenes. The long-tailed distribution of labeled instances is a primary challenge in HOI detection, promoting research in few-shot and…
Object-centric representations have recently enabled significant progress in tackling relational reasoning tasks. By building a strong object-centric inductive bias into neural architectures, recent efforts have improved generalization and…
Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…
In reinforcement learning (RL), an autonomous agent learns to perform complex tasks by maximizing an exogenous reward signal while interacting with its environment. In real-world applications, test conditions may differ substantially from…