The Developments and Challenges towards Dexterous and Embodied Robotic Manipulation: A Survey

2025-07-15

AI Summary

Dexterous manipulation by anthropomorphic robotic hands remains a core challenge in robotics, hindered by data scarcity, poor skill generalization, and the sim-to-real gap. Method: This paper proposes a unified framework integrating simulation-based environment construction, human teleoperated demonstration collection, imitation learning, and deep reinforcement learning. It innovatively unifies multi-source data acquisition paradigms with hierarchical skill learning to establish the first systematic research framework for embodied dexterous manipulation. Contribution/Results: Experimental evaluation demonstrates significant improvements in manipulation robustness and cross-task transferability. The work clarifies the technical evolution trajectory and identifies key bottlenecks, while providing a scalable methodological foundation and concrete research directions for embodied intelligence–driven dexterous manipulation.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Achieving human-like dexterous robotic manipulation remains a central goal and a pivotal challenge in robotics. The development of Artificial Intelligence (AI) has allowed rapid progress in robotic manipulation. This survey summarizes the evolution of robotic manipulation from mechanical programming to embodied intelligence, alongside the transition from simple grippers to multi-fingered dexterous hands, outlining key characteristics and main challenges. Focusing on the current stage of embodied dexterous manipulation, we highlight recent advances in two critical areas: dexterous manipulation data collection (via simulation, human demonstrations, and teleoperation) and skill-learning frameworks (imitation and reinforcement learning). Then, based on the overview of the existing data collection paradigm and learning framework, three key challenges restricting the development of dexterous robotic manipulation are summarized and discussed.

Problem

• Achieving human-like dexterous robotic manipulation in robotics
• Transition from simple grippers to multi-fingered dexterous hands
• Challenges in dexterous manipulation data collection and skill-learning

Innovation

• Dexterous manipulation via simulation and teleoperation
• Skill-learning with imitation and reinforcement
• Transition from grippers to multi-fingered hands