XI International Conference on Interactive Collaborative Robotics (ICR 2026)

Igor Bychkov

Director of the Matrosov Institute for System Dynamics and Control Theory, Deputy Chairman of the Siberian Branch of the Russian Academy of Sciences (SB RAS) for Scientific Work – Scientific Supervisor of the Irkutsk Branch of SB RAS,

Irkutsk, Russia

Plenary Speech 1:

Adaptive Control Strategies for Autonomous Robot Groups Operating in Obstacle-prone Environments

Abstract:

One of the fundamental tasks in group control of autonomous mobile robots is the efficient routing of a group while performing a given set of distributed tasks.
The presence of unaccounted physical obstacles in this context can disrupt communication within the group, creating a risk of losing one or multiple robots. This is especially important when the group moves in a specific formation, the choice of which is determined by the current task and the surrounding environment.
To compensate for insufficient situational awareness, various solutions are used, including additional observer robots that form a higher-level group, which possesses enhanced situational awareness and is capable of maintaining communication with the lower-level group within line of sight.
The talk presents original control strategies for groups of autonomous robots that enable decentralized adaptation of formations and interaction modes in multi-level groups in response to environmental dynamics and squad changes. Unlike centralized solutions, the proposed methods do not rely on a single leader or a global coordinator.
Instead, each robot independently makes decisions based on local information from neighboring agents and environmental conditions. This ensures scalability, robustness to individual robot failures, and adaptability to dynamically changing environments.

Konstantin Yakovlev

Leading Researcher, Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences, Moscow, Russia, Docent, Saint Petersburg University,

St. Petersburg, Russia

Plenary Speech 2:

Multi-agent Path Finding: Algorithmic and Learning-based Solutions

Abstract:

Coordinating a team of mobile robots that simultaneously move and accomplish tasks in a shared environment (e.g., wheeled robots in a warehouse, driverless cars in a parking lot, etc.) is a challenging problem that comes in different flavors. The Multi-Agent Path Finding (MAPF) formalism provides a fundamental abstraction for this problem, enabling the development of algorithms with strong theoretical guarantees.
Heuristic search has been highly successful in this domain, producing optimal or bounded-suboptimal solutions with proven guarantees. Rule-based solvers and optimization techniques have also proven to be effective tools to tackle MAPF by providing high-quality solutions within a much lower computational budget. Still, most of the modern search-based and rule-based MAPF solvers intrinsically assume that the multi-agent system is controlled in a centralized fashion and it is not trivial to adapt them to real-world constraints like partial observability and limited communication.
This is where ML-based approaches may come on stage and overcome the limitations of conventional planning-based methods. This talk explores how heuristic search may be integrated with machine learning (i.e. deep reinforcement learning, imitation learning, transformers, large-scale learning) to create new generation of (decentralized) MAPF solvers.

Minglei Fu

College of Information Engineering, Zhejiang University of Technology,

Hangzhou, China

Plenary Speech 3:

High-precision positioning and navigation of intelligent robots in complex dynamic environments

Abstract:

The problems of high-precision positioning and navigation of intelligent ground robots under dynamic interference conditions (tree canopy shading, multipath effects, and onboard electromagnetic interference) are considered. Limitations of the classical EKF approach with direct fixing of dual-frequency ambiguities are shown.
A robust RTK method combining wide-lane tracking and a progressive Gaussian filter is proposed. Real experiments with quadruped ground robotic platforms in a real environment demonstrate a reduction in horizontal trajectory error to 0.13 m and vertical error to 0.18 m.
The developed solutions are intended for navigation of autonomous robots in shaded and industrial environments.

Du Libin

Research Progress on Marine Environment Perception and Intelligent Detection Robots.

Plenary Speech 4:

Robotics in Construction: Advances, Examples and What's Next?

Abstract:

High-precision marine environmental perception and intelligent detection serve as an essential foundation for deep-sea resource development, ecological environment protection, marine scientific research, and marine security guarantee. Aiming at prominent problems such as insufficient detection accuracy, poor sensor stability, and limited autonomous operation capability of robots under complex ocean disturbances and extreme deep-sea working conditions, this report focuses on two core components:
high-precision marine sensor technology and intelligent detection robots, and systematically reviews the latest research progress and application achievements of relevant technologies. Firstly, it elaborates on the technological breakthroughs of high-precision marine hydrological sensors in terms of high-precision acquisition, noise suppression, and product development.
Secondly, it summarizes the technological iteration achievements of underwater intelligent operation robots and agile detection robots in multi-source sensor information fusion, anti-interference perception in complex sea areas, high-precision autonomous navigation, and intelligent operation. Finally, it prospects the development trends of this field.
In the future, marine perception technologies will achieve continuous breakthroughs in the directions of high-precision integration of sensors, deep-sea adaptation of detection equipment, high-precision collaborative detection of robot clusters, and long-term stable autonomous operation, providing theoretical reference and technical support for the iterative upgrading of high-precision marine perception technologies, the optimization and upgrading of intelligent detection robots, and their engineering implementation.