Special Topic: Embodied Intelligence
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar

Causal action empowerment for efficient reinforcement learning in embodied agents
Cao H Y, Feng F, Huo J, et al
Sci China Inf Sci, 2025, 68(5): 150201
Keywords: reinforcement learning; causal; empowerment; embodied agents; sample efficiency
Cite as: Cao H Y, Feng F, Huo J, et al. Causal action empowerment for efficient reinforcement learning in embodied agents. Sci China Inf Sci, 2025, 68(5): 150201, doi: 10.1007/s11432-024-4396-3

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Learning future representation with synthetic observations for sample-efficient reinforcement learning
Liu X, Chen Y R, Li H R, et al
Sci China Inf Sci, 2025, 68(5): 150202
Keywords: deep reinforcement learning; DRL; RL for embodied agents; RL for continuous control; image-based RL; self-supervised learning; RL visual pre-training
Cite as: Liu X, Chen Y R, Li H R, et al. Learning future representation with synthetic observations for sample-efficient reinforcement learning. Sci China Inf Sci, 2025, 68(5): 150202, doi: 10.1007/s11432-024-4380-4

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

A trajectory-level robot skill learning method based on fuzzy systems
Zeng C, Deng Z, Ti B Y, et al
Sci China Inf Sci, 2025, 68(5): 150203
Keywords: robot skill learning; movement primitives; TSK fuzzy systems; gradient descent; robotics
Cite as: Zeng C, Deng Z, Ti B Y, et al. A trajectory-level robot skill learning method based on fuzzy systems. Sci China Inf Sci, 2025, 68(5): 150203, doi: 10.1007/s11432-024-4322-6

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

A zeroth-order stochastic implicit method for bilevel-structured actor-critic schemes
Tao H C, Cui S S, Li Z, et al
Sci China Inf Sci, 2025, 68(5): 150204
Keywords: actor-critic; bilevel optimization; zeroth-order algorithm; implicit programming; stochastic approximation
Cite as: Tao H C, Cui S S, Li Z, et al. A zeroth-order stochastic implicit method for bilevel-structured actor-critic schemes. Sci China Inf Sci, 2025, 68(5): 150204, doi: 10.1007/s11432-024-4397-7

Special Topic: Embodied Intelligence
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar

Formation control and path planning of multi-robot systems via large language models
Xue D, Zhou X J, Wang M, et al
Sci China Inf Sci, 2025, 68(5): 150205
Keywords: multi-robot systems; formation control; path planning; obstacle avoidance; large language models
Cite as: Xue D, Zhou X J, Wang M, et al. Formation control and path planning of multi-robot systems via large language models. Sci China Inf Sci, 2025, 68(5): 150205, doi: 10.1007/s11432-024-4290-4

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Multi-UAV trajectory planning with field-of-view sharing mechanism in cluttered environments: application to target tracking
Rao K, Yan H C, Yang P H, et al
Sci China Inf Sci, 2025, 68(5): 150206
Keywords: multi-UAV; target tracking; trajectory planning; field-of-view sharing mechanism
Cite as: Rao K, Yan H C, Yang P H, et al. Multi-UAV trajectory planning with field-of-view sharing mechanism in cluttered environments: application to target tracking. Sci China Inf Sci, 2025, 68(5): 150206, doi: 10.1007/s11432-024-4394-6

Special Topic: Embodied Intelligence
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar

VF-Nav: visual floor-plan-based point-goal navigation
Shen W T, Meng Z Y, Gu P F, et al
Sci China Inf Sci, 2025, 68(5): 150207
Keywords: point-goal navigation; brain-inspired localization; floor plan
Cite as: Shen W T, Meng Z Y, Gu P F, et al. VF-Nav: visual floor-plan-based point-goal navigation. Sci China Inf Sci, 2025, 68(5): 150207, doi: 10.1007/s11432-024-4384-6

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Autonomous embodied navigation task generation from natural language dialogues
Xu H F, Li Y C, Ma L M, et al
Sci China Inf Sci, 2025, 68(5): 150208
Keywords: proactive robot; robot navigation; service robot; large language model
Cite as: Xu H F, Li Y C, Ma L M, et al. Autonomous embodied navigation task generation from natural language dialogues. Sci China Inf Sci, 2025, 68(5): 150208, doi: 10.1007/s11432-024-4404-4

Special Topic: Embodied Intelligence
RESEARCH PAPER Supplementary Webpage Webpage-cn SpringerLink Google Scholar

PEAR: phrase-based hand-object interaction anticipation
Zhang Z C, Luo H C, Zhai W, et al
Sci China Inf Sci, 2025, 68(5): 150209
Keywords: hand-object interaction; first-person perspective; trajectory forecasting; hand pose prediction; embodied intelligence
Cite as: Zhang Z C, Luo H C, Zhai W, et al. PEAR: phrase-based hand-object interaction anticipation. Sci China Inf Sci, 2025, 68(5): 150209, doi: 10.1007/s11432-024-4405-4

Special Topic: Embodied Intelligence
RESEARCH PAPER Webpage Webpage-cn SpringerLink Google Scholar

Embodied intelligence in RO/RO logistic terminal: autonomous intelligent transportation robot architecture
Xu Y K, Bao R J, Zhang L, et al
Sci China Inf Sci, 2025, 68(5): 150210
Keywords: embodied intelligence; transportation robot; RO/RO logistic terminal; detection; autonomous planning
Cite as: Xu Y K, Bao R J, Zhang L, et al. Embodied intelligence in RO/RO logistic terminal: autonomous intelligent transportation robot architecture. Sci China Inf Sci, 2025, 68(5): 150210, doi: 10.1007/s11432-024-4395-7