Data-driven methods such as reinforcement and imitation learning have achieved remarkable success in robot autonomy. However, their data-centric nature still hinders them from generalizing well to ever-changing environments. Moreover, labeling data for robotic tasks is often impractical and expensive. To overcome these challenges, we introduce a new self-supervised neuro-symbolic (NeSy) computational framework, imperative learning (IL), for robot autonomy, leveraging the generalization abilities of symbolic reasoning. The framework of IL consists of three primary components: a neural module, a reasoning engine, and a memory system. We formulate IL as a special bilevel optimization (BLO), which enables reciprocal learning over the three modules. This overcomes the label-intensive obstacles associated with data-driven approaches and takes advantage of symbolic reasoning concerning logical reasoning, physical principles, geometric analysis, etc. We discuss several optimization techniques for IL and verify their effectiveness in five distinct robot autonomy tasks including path planning, rule induction, optimal control, visual odometry, and multi-robot routing. Through various experiments, we show that IL can significantly enhance robot autonomy capabilities and we anticipate that it will catalyze further research across diverse domains.
Intelligent unmanned systems for ground, sea, aviation, and aerospace application are important research directions for the new generation of artificial intelligence in China. Intelligent unmanned systems are also important carriers of interactive mapping between physical space and cyberspace in the process of the digitization of human society. Based on the current domestic and overseas development status of unmanned systems for ground, sea, aviation, and aerospace application, this paper reviewed the theoretical problems and research trends of multi-agent cross-domain cooperative perception. The scenarios of multi-agent cooperative perception tasks in different areas were deeply investigated and analyzed, the scientific problems of cooperative perception were analyzed, and the development direction of multi-agent cooperative perception theory research for solving the challenges of the complex environment, interactive communication, and cross-domain tasks was expounded.
With the changes in human work and lifestyle, the incidence of cervical spondylosis is increasing substantially, especially for adolescents. Cervical spine exercises are an important means to prevent and rehabilitate cervical spine diseases, but no mature unmanned evaluating and monitoring system for cervical spine rehabilitation training has been proposed. Patients often lack the guidance of a physician and are at risk of injury during the exercise process. In this paper, we first propose a cervical spine exercise assessment method based on a multi-task computer vision algorithm, which can replace physicians to guide patients to perform rehabilitation exercises and evaluations. The model based on the Mediapipe framework is set up to construct a face mesh and extract features to calculate the head pose angles in 3-DOF (three degrees of freedom). Then, the sequential angular velocity in 3-DOF is calculated based on the angle data acquired by the computer vision algorithm mentioned above. After that, the cervical vertebra rehabilitation evaluation system and index parameters are analyzed by data acquisition and experimental analysis of cervical vertebra exercises. A privacy encryption algorithm combining YOLOv5 and mosaic noise mixing with head posture information is proposed to protect the privacy of the patient’s face. The results show that our algorithm has good repeatability and can effectively reflect the health status of the patient’s cervical spine.
9 February 2026 in IEEE Robotics and Automation Letters
Real-world task planning requires long-horizon reasoning over large sets of objects with complex relationships and attributes, leading to a combinatorial explosion for classical symbolic planners. To prune the search space, recent methods prioritize searching on a simplified task only containing a few “important” objects predicted by a neural network. However, such a simple neuro-symbolic (NeSy) integration risks omitting critical objects and wasting resources on unsolvable simplified tasks. To enable Fast and reliable planning, we introduce a NeSy relaxation strategy (Flax), combining neural importance prediction with symbolic expansion. Specifically, we first learn a graph neural network to predict object importance to create a simplified task and solve it with a symbolic planner. Then, we solve a rule-relaxed task to obtain a quick rough plan, and reintegrate all referenced objects into the simplified task to recover any overlooked but essential elements. Finally, we apply complementary rules to refine the updated task, keeping it both reliable and compact. Extensive experiments are conducted on both synthetic and real-world maze navigation benchmarks where a robot must traverse through a maze and interact with movable obstacles. The results show that Flax boosts the average success rate by 20.82% and cuts mean wall-clock planning time by 17.65% compared with the state-of-the-art NeSy baseline. We expect that Flax offers a practical path toward fast, scalable, long-horizon task planning in complex environments.
Artificial intelligence has been increasingly applied to smart city development and field practice. As a result, the problem about the exponential growth of city data and the cost of computing power has become increasingly prominent. Edge computing and multi-agent collaboration tend to be an emerging technology paradigm that enables the balance of the above contradiction. Based on the edge computing and multi-agent theory, we put forward the concept of EIPA (Edge Intelligent Perception Agent) and its system architecture. The hardware design methodologies of mobile EIPA and stationary EIPA were expounded in detail, and then the algorithm model of intelligent monitoring in the urban park was introduced. The whole system is being tested and verified in the urban industry park and residential quarter. The utility results of EIPA for pollutant diffusion center location are discussed, which confirmed the system's effectiveness. The limitations of current work and recommendations for future work are proposed at last.