The design, construction, and use of robots, as well as the use of computer systems for their control, sensory feedback, and information processing.
The paper introduces ROBOFUME, a system that allows robots to learn new tasks autonomously with minimal human intervention. The system pre-trains a multi-task manipulation policy using diverse datasets, and then…
Continue readingThe article discusses HELPER, an embodied agent that uses retrieval-augmented situated prompting of Large Language Models (LLMs) to parse free-form dialogue, instructions, and corrections from humans and vision-language models to…
Continue readingThis paper presents a human-robot mutual learning system for language acquisition grounded in homeostatic needs. The system uses differential outcomes training (DOT) where the robot provides specific feedback based on…
Continue readingThe paper provides an overview of the emerging field of social robotics and mediation research. It highlights the potential of a social robot mediator in a multiparty setting, particularly in…
Continue readingThis article presents EUREKA, a human-level reward design algorithm powered by Large Language Models (LLMs). It employs LLMs’ zero-shot generation and code-writing abilities to perform evolutionary optimization over reward code….
Continue readingThis academic paper discusses the challenge of integrating multiple robotic and Artificial Intelligence (AI) techniques to model complex robot behaviour. The authors propose using a formal framework to map the…
Continue readingThis article presents a novel approach to real-time motion prediction in autonomous driving systems. The authors introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), and the Heterogeneous Polyline…
Continue readingThis work is about a self-supervised method, FSD, for recognizing 3D objects from a single RGB-D image. It aims to predict the 3D shape, size, and 6D pose of objects,…
Continue readingThe article discusses a framework for learning contact-rich manipulation skills that are crucial for robots. The learning process is challenging due to data inefficiency in real world applications and the…
Continue readingThe article discusses a new aerial robot design that can perform precise power tool tasks on vertical walls. The robot combines a quadrotor with active suction cups for perching on…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
