相关论文: ThinkBot: Embodied Instruction Following with Thou…

Language is often considered a key aspect of human thinking, providing us with exceptional abilities to generalize, explore, plan, replan, and adapt to new situations. However, Reinforcement Learning (RL) agents are far from human-level…

There is a growing interest in the community in making an embodied AI agent perform a complicated task while interacting with an environment following natural language directives. Recent studies have tackled the problem using ALFRED, a…

Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…

Humans can covertly track the position of an object, even if the object is temporarily occluded. What are the neural mechanisms underlying our capacity to track moving objects when there is no physical stimulus for the brain to track? One…

Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…

Summary of results (project period 1. 10. 2008 - 30. 9. 2009) of SNFS Project "From locomotion to cognition" The research that we have been involved in, and will continue to do, starts from the insight that in order to understand and design…

Embodied agents capable of complex physical skills can improve productivity, elevate life quality, and reshape human-machine collaboration. We aim at autonomous training of embodied agents for various tasks involving mainly large foundation…

Flexible manufacturing processes demand robots to easily adapt to changes in the environment and interact with humans. In such dynamic scenarios, robotic tasks may be programmed through learning-from-demonstration approaches, where a…

An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon…

Current embodied intelligent systems still face a substantial gap between high-level reasoning and low-level physical execution in open-world environments. Although Vision-Language-Action (VLA) models provide strong perception and intuitive…

Recent years have witnessed many successful trials in the robot learning field. For contact-rich robotic tasks, it is challenging to learn coordinated motor skills by reinforcement learning. Imitation learning solves this problem by using a…

This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…

While natural language offers a convenient shared interface for humans and robots, enabling robots to interpret and follow language commands remains a longstanding challenge in manipulation. A crucial step to realizing a performant…

Summary of results in last project period (1. 10. 2009 - 30. 9. 2010) of SNFS Project "From locomotion to cognition" The research that we have been involved in, and will continue to do, starts from the insight that in order to understand…

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself,…

Natural language is perhaps the most flexible and intuitive way for humans to communicate tasks to a robot. Prior work in imitation learning typically requires each task be specified with a task id or goal image -- something that is often…

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

Although in the literature it is common to find predictors and inference systems that try to predict human intentions, the uncertainty of these models due to the randomness of human behavior has led some authors to start advocating the use…

Current language-guided robotic manipulation systems often require low-level action-labeled datasets for imitation learning. While object-centric flow prediction methods mitigate this issue, they remain limited to scenarios involving rigid…

Theory of Mind (ToM), the ability to track others epistemic state, makes humans efficient collaborators. AI agents need the same capacity in multi agent settings, yet existing benchmarks mostly test literal ToM by asking direct belief…