IEEE Transactions on Robotics (T-RO) papers (other than communication items and survey papers) are eligible to be presented at certain upcoming IEEE RAS fully- or co-sponsored conferences such as the IEEE International Conference on Robotics and Automation (ICRA), the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), or the IEEE International Conference on Automation Science and Engineering (CASE). For more information, please see http://www.ieee-ras.org/publications/t-ro.

Scope

T-RO publishes fundamental papers on all aspects of robotics, featuring interdisciplinary approaches from computer science, control systems, electrical engineering, mathematics, mechanical engineering, and other fields. Robots and intelligent machines and systems are critical in areas such as industrial applications; service and personal assistants; surgical operations; space, underwater, and remote exploration; entertainment; safety, search, and rescue; military applications; agriculture applications; and intelligent vehicles. Special emphasis is placed on intelligent machines and systems for unstructured environments, where a significant portion of the environment is unknown and cannot be directly sensed or controlled. 

Examples of topics that fall within the scope of T-RO include:

    Design: mechanisms and actuation; robots with flexible elements; limbed structures; parallel and hybrid mechanisms; robot hands; snake-like and continuum robots; soft robots; modular robots; biomimetic and bioinspired robots; wheeled robots; underwater robots; flying robots; micro-/nanorobots; performance evaluation and optimization; modeling, identification, calibration
    Sensing and Perception: foundations of sensing and estimation; force and tactile sensing; range, sonar, and inertial Sensing; GPS and odometry; 3-D vision; object recognition; visual servoing; multisensor data fusion
    Manipulation, Interfaces, and Programming: motion and force planning and control for manipulation tasks; contact modeling and manipulation; grasping; cooperative manipulation; mobility and manipulation; haptics; active manipulation for perception; telerobotics; networked robots; robotic systems architectures and programming
    Moving in the Environment: world modeling; simultaneous localization and mapping (SLAM); motion planning and obstacle avoidance; modeling and control of legged robots, wheeled mobile robots, robots on rough terrain, underwater robots, aerial robots, and multiple mobile robot systems
    Robots at Work: industrial robotics; space robotics; robotics in agriculture and forestry; robotics in construction; robotics in hazardous applications; robotics in mining; search and rescue robotics; robot surveillance and security; intelligent vehicles; medical robotics and computer-integrated surgery; rehabilitation and healthcare robotics; domestic robotics
    Robots and Humans: humanoids; physical and cognitive human-robot interaction; human-robot augmentation; social and socially assistive robotics; learning from humans; behavior-based systems; AI reasoning methods for robotics; biologically-inspired robotics; evolutionary robotics; neurorobotics; perceptual robotics; robo-ethics

Papers describing specific current (industrial and beyond) applications are encouraged, provided that the paper convincingly demonstrates that it represents the best current practice, detailed characteristics and performance are included, and it is of general interest.

Special Issue on Foundation Models for Robotics
提出日: 2025-09-01

Important Dates

    Submissions open: September 1, 2025
    Submissions close: November 30, 2025
    Expected publication date: July 2026

Guest Editors

Nicola Bezzo, University of Virginia, USA
Shoaib Ehsan, University of Southampton, UK
Dinesh Jayaraman, University of Pennsylvania, USA
Jiachen Li, University of California, Riverside, USA
Zhijun Li, Tongji University, China
Wei Pan, University of Manchester, UK
Harold Soh, National University of Singapore, Singapore
Chaoyang Song, Southern University of Science and Technology, China
Rudolf Lioutikov, Karlsruhe Institute of Technology, Germany
 
Overseeing Editor

Jeannette Bohg, Stanford University, USA
 
Aims and Scope

Original call for papers document.

Foundation models in robotics aim to provide systems with broad generalization capabilities across tasks, environments, and embodiments by leveraging large-scale pretraining on diverse data sources. Inspired by the success of foundation models in language and vision, the robotics community is actively exploring their use and adaptation across a wide range of robot tasks. Early successes include using vision-language models (VLMs) for perception and large language models (LLMs) for high-level planning.

This special collection focuses on two goals: (1) understanding the current capabilities and limitations of foundation models in robotics contexts, and (2) advancing the design and adaptation of such models to address these limitations. We encourage contributions that offer insight into where current foundation models fall short in real-world robot settings, and how new architectures, training regimes, or system design might close these gaps. Within this context, the scope of this special issue includes, but is not limited to, the following topics:

    Reliable evaluation and comparison of capabilities
    Reliance on limited robot training data
    Retraining or post-training for improving performance on out-of-distribution tasks
    Generalization across diverse robot embodiments beyond the most common morphologies
    Spatial awareness and reasoning, geometric understanding, spatial precision
    Multimodality including tactile sensing and force feedback
    Low-latency onboard resource-constrained execution
    Safety, explainability, and trustworthiness