相关论文: Incremental procedural and sensorimotor learning i…

Enabling humanoid robots to clean rooms has long been a pursued dream within humanoid research communities. However, many tasks require multi-humanoid collaboration, such as carrying large and heavy furniture together. Given the scarcity of…

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not…

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data,…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Interactive robot learning is a challenging problem as the robot is present with human users who expect the robot to learn novel skills to solve novel tasks perpetually with sample efficiency. In this work we present a framework for robots…

State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first…

Interactive Imitation Learning (IIL) allows agents to acquire desired behaviors through human interventions, but current methods impose high cognitive demands on human supervisors. We propose the Adaptive Intervention Mechanism (AIM), a…

The requirement for autonomous robots to exhibit higher-level cognitive skills by planning and adapting in an ever-changing environment is indeed a great challenge for the AI community. Progress has been made in the automated planning…

Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immediate perception and accumulated experience across tasks. However, most existing LLM-based…

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…

AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Autonomous agents (robots) face tremendous challenges while interacting with heterogeneous human agents in close proximity. One of these challenges is that the autonomous agent does not have an accurate model tailored to the specific human…

The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence. Intrinsically Motivated Goal Exploration Processes give learning agents a…

Letting robots emulate human behavior has always posed a challenge, particularly in scenarios involving multiple robots. In this paper, we presented a framework aimed at achieving multi-agent reinforcement learning for robot control in…

Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding methods for…

Interactions are central to intelligent reasoning and learning abilities, with the interpretation of abstract knowledge guiding meaningful interaction with objects in the environment. While humans readily adapt to novel situations by…

Deep learning often requires the manual collection and annotation of a training set. On robotic platforms, can we partially automate this task by training the robot to be curious, i.e., to seek out beneficial training information in the…

In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However,…

Traditional control and planning for robotic manipulation heavily rely on precise physical models and predefined action sequences. While effective in structured environments, such approaches often fail in real-world scenarios due to…