Related papers: Self-evolving Embodied AI
This work presents an embodied agent that can adapt its semantic segmentation network to new indoor environments in a fully autonomous way. Because semantic segmentation networks fail to generalize well to unseen environments, the agent…
The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that policies are treated as being separate from the world they…
Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational…
Semantic information in embodied AI is inherently multi-source and multi-stage, making it challenging to fully leverage for achieving stable perception-to-action loops in real-world environments. Early studies have combined manual…
Embodied agents operating in complex and uncertain environments face considerable challenges. While some advanced agents handle complex manipulation tasks with proficiency, their success often hinges on extensive training data to develop…
Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software…
The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with the advent of deep reinforcement learning and increased…
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…
Scientists have traditionally limited the mechanisms of social cognition to one brain, but recent approaches claim that interaction also realizes cognitive work. Experiments under constrained virtual settings revealed that interaction…
Agent-based Internet of Things (IoT) applications have recently emerged as applications that can involve sensors, wireless devices, machines and software that can exchange data and be accessed remotely. Such applications have been proposed…
Embodied AI is a prominent research topic in both academia and industry. Current research centers on completing tasks based on explicit user instructions. However, for robots to integrate into human society, they must understand which…
Artificial intelligence (AI) systems are evolving beyond passive tools into autonomous agents capable of reasoning, adapting, and acting with minimal human intervention. Despite their growing presence, a structured framework is lacking to…
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory…
Recent developments in artificial intelligence (AI) have permeated through an array of different immersive environments, including virtual, augmented, and mixed realities. AI brings a wealth of potential that centers on its ability to…
Experiential AI is presented as a research agenda in which scientists and artists come together to investigate the entanglements between humans and machines, and an approach to human-machine learning and development where knowledge is…
Wireless communication is evolving into an agent era, where numerous intelligent agents equipped with perception, reasoning, and interaction capabilities will operate in highly dynamic wireless environments. To complete diverse complex…
Recent advancements in large foundation models have remarkably enhanced our understanding of sensory information in open-world environments. In leveraging the power of foundation models, it is crucial for AI research to pivot away from…
We describe a framework for research and evaluation in Embodied AI. Our proposal is based on a canonical task: Rearrangement. A standard task can focus the development of new techniques and serve as a source of trained models that can be…
We present a self-supervised method to improve an agent's abilities in describing arbitrary objects while actively exploring a generic environment. This is a challenging problem, as current models struggle to obtain coherent image captions…
Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded. In contrast, humans and other embodied agents have the ability to move in the environment, and actively control the viewing…