Related papers: Learning body-affordances to simplify action space…
In the ecological approach to perception and action, information that specifies affordances is available in the energy arrays surrounding organisms, and this information is detected by organisms in order to perceptually guide their actions.…
When a robot encounters a novel object, how should it respond$\unicode{x2014}$what data should it collect$\unicode{x2014}$so that it can find the object in the future? In this work, we present a method for learning image features of an…
Embodied AI is a recent research area that aims at creating intelligent agents that can move and operate inside an environment. Existing approaches in this field demand the agents to act in completely new and unexplored scenes. However,…
Learning object affordances is an effective tool in the field of robot learning. While the data-driven models investigate affordances of single or paired objects, there is a gap in the exploration of affordances of compound objects composed…
Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…
The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from ambient data. This capability creates a fundamental tension…
Intelligent agents accomplish different tasks by utilizing various objects based on their affordance, but how to select appropriate objects according to task context is not well-explored. Current studies treat objects within the affordance…
Acquiring knowledge about object interactions and affordances can facilitate scene understanding and human-robot collaboration tasks. As humans tend to use objects in many different ways depending on the scene and the objects' availability,…
The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success,…
The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks.…
Multi-agent systems exhibit complex behaviors that emanate from the interactions of multiple agents in a shared environment. In this work, we are interested in controlling one agent in a multi-agent system and successfully learn to interact…
Grounding 3D object affordance seeks to locate objects' ''action possibilities'' regions in the 3D space, which serves as a link between perception and operation for embodied agents. Existing studies primarily focus on connecting visual…
Learning to perform activities through demonstration requires extracting meaningful information about the environment from observations. In this research, we investigate the challenge of planning high-level goal-oriented actions in a…
The increase in available computing power and the Deep Learning revolution have allowed the exploration of new topics and frontiers in Artificial Intelligence research. A new field called Embodied Artificial Intelligence, which places at…
Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…
Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied…
Learning how to navigate among humans in an occluded and spatially constrained indoor environment, is a key ability required to embodied agent to be integrated into our society. In this paper, we propose an end-to-end architecture that…
Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…
In this study, we address the problem of open-vocabulary mobile manipulation, where a robot is required to carry a wide range of objects to receptacles based on free-form natural language instructions. This task is challenging, as it…
Complex physical tasks entail a sequence of object interactions, each with its own preconditions -- which can be difficult for robotic agents to learn efficiently solely through their own experience. We introduce an approach to discover…