Uncertainty-Aware Perception, Planning and Control for Intelligent Robots

Introduction: With the increasing deployment of robots in complex real-world environments, uncertainties arising from dynamic obstacles, imperfect models, unreliable sensing, and environmental changes have become major challenges to robotic autonomy, robustness, and safety. Conventional robotic systems often adopt a modular pipeline in which perception, planning, and motion control are designed separately. Although effective in structured scenarios, such fragmented architectures may suffer from limited adaptability and degraded performance in uncertain, dynamic, or partially observable environments.

This Special Session aims to bring together recent advances in uncertainty-aware perception, motion planning, and control for intelligent robots. It focuses on integrated and closed-loop robotic frameworks that enable robots to perceive, reason, plan, and act robustly under uncertainty. Both theoretical developments and practical applications are encouraged, particularly those addressing real-time decision-making, safe motion generation, adaptive control, and robust task execution in complex environments.

Topics of Interest include, but are not limited to:

1. Multi-modal perception and sensor fusion for robotics
2. Environmental modeling and state estimation under uncertainty
3. Robust and adaptive motion planning in dynamic environments
4. Integrated perception-planning-control frameworks
5. Learning-based planning and control for uncertain robotic systems
6. Safety-critical control and collision avoidance for autonomous robots
   

Organizers:

Jianliang Mao, Shanghai University of Electric Power, China Jianliang Mao is an Associate Professor at Shanghai University of Electric Power, serves as the Enterprise Vice Director of Science and Technology of Jiangsu Province and recipient of the Jiangsu Provincial Double Innovation Doctor Program. He received his Bachelor’s degree in Automation in 2011, Master’s degree in Control Engineering in 2014, and Doctoral degree in Control Theory and Control Engineering in 2018, all from Southeast University. His main research interests include model predictive control, reinforcement learning, visual interactive control and their applications in robotic systems. He has presided 9 projects including the NSFC, Shanghai Science and Technology Commission, as well as industry-university-research cooperation projects of State Grid Corporation of China and China Southern Power Grid. He has published 18 SCI papers as the first author or corresponding author in journals such as TRO, TCST, TIE and TCYB. He has been granted 23 China patents and 1 US patent, and participated in compiling 2 industrial standards for robot inspection. Currently, he acts as a Young Editorial Board Member of Intelligence & Robotics and AI and Autonomous Systems.

Xiangyang Liu, Hefei University of Technology, China Xiangyang Liu is a Lecturer at Hefei University of Technology. He obtained his B.Sc. degree in Automation from China University of Geosciences (Wuhan) in 2016, and his Ph.D. degree in Control Science and Engineering from Southeast University in 2022, and then he joined the Central Research Institute of Huawei Technologies Co., Ltd. From January 2026, he is in the Department of Automation, Hefei University of Technology. He has published some papers in international journals such as IEEE Transactions and Automatica, and holds several invention patents. His research interests include anti-disturbance control, predictive control, robot visual servo system control.

Submission Guideline:

Please submit your manuscript via Online Submission System: https://easychair.org/conferences/?conf=rcae2026
Please choose "Special Session 12"