arXiv subjects

Jiyu Cheng

Publications and source records attributed to Jiyu Cheng.

7 recordsLinked to original sources

arXiv2026

Skill-Aware Diffusion for Generalizable Robotic Manipulation

Robust generalization in robotic manipulation is crucial for robots to adapt flexibly to diverse environments. Existing methods usually improve generalization by scaling data and networks, but model tasks independently and overlook skill-level information. Observing that tasks within the same skill share similar motion patterns, we propose Skill-Aware Diffusion (SADiff), which explicitly incorporates skill-level information to improve generalization. SADiff learns skill-specific representations through a skill-aware encoding module with learnable skill tokens, and conditions a skill-constrained diffusion model to generate object-centric motion flow. A skill-retrieval transformation strategy further exploits skill-specific trajectory priors to refine the mapping from 2D motion flow to executable 3D actions. Furthermore, we introduce IsaacSkill, a high-fidelity dataset containing fundamental robotic skills for comprehensive evaluation and sim-to-real transfer. Experiments in simulation and real-world settings show that SADiff achieves good performance and generalization across various manipulation tasks. Code, data, and videos are available at https://sites.google.com/view/sa-diff.

cs.RO↗

arXiv2026

Dual-Attention Heterogeneous GNN for Multi-robot Collaborative Area Search via Deep Reinforcement Learning

In multi-robot collaborative area search, a key challenge is to dynamically balance the two objectives of exploring unknown areas and covering specific targets to be rescued. Existing methods are often constrained by homogeneous graph representations, thus failing to model and balance these distinct tasks. To address this problem, we propose a Dual-Attention Heterogeneous Graph Neural Network (DA-HGNN) trained using deep reinforcement learning. Our method constructs a heterogeneous graph that incorporates three entity types: robot nodes, frontier nodes, and interesting nodes, as well as their historical states. The dual-attention mechanism comprises the relational-aware attention and type-aware attention operations. The relational-aware attention captures the complex spatio-temporal relationships among robots and candidate goals. Building on this relational-aware heterogeneous graph, the type-aware attention separately computes the relevance between robots and each goal type (frontiers vs. points of interest), thereby decoupling the exploration and coverage from the unified tasks. Extensive experiments conducted in interactive 3D scenarios within the iGibson simulator, leveraging the Gibson and MatterPort3D datasets, validate the superior scalability and generalization capability of the proposed approach.

cs.RO↗

arXiv2024

Asymmetric Information Enhanced Mapping Framework for Multirobot Exploration based on Deep Reinforcement Learning

Despite the great development of multirobot technologies, efficiently and collaboratively exploring an unknown environment is still a big challenge. In this paper, we propose AIM-Mapping, a Asymmetric InforMation Enhanced Mapping framework. The framework fully utilizes the privilege information in the training process to help construct the environment representation as well as the supervised signal in an asymmetric actor-critic training framework. Specifically, privilege information is used to evaluate the exploration performance through an asymmetric feature representation module and a mutual information evaluation module. The decision-making network uses the trained feature encoder to extract structure information from the environment and combines it with a topological map constructed based on geometric distance. Utilizing this kind of topological map representation, we employ topological graph matching to assign corresponding boundary points to each robot as long-term goal points. We conduct experiments in real-world-like scenarios using the Gibson simulation environments. It validates that the proposed method, when compared to existing methods, achieves great performance improvement.

cs.MA↗

arXiv2023

Autonomous and Adaptive Role Selection for Multi-robot Collaborative Area Search Based on Deep Reinforcement Learning

In the tasks of multi-robot collaborative area search, we propose the unified approach for simultaneous mapping for sensing more targets (exploration) while searching and locating the targets (coverage). Specifically, we implement a hierarchical multi-agent reinforcement learning algorithm to decouple task planning from task execution. The role concept is integrated into the upper-level task planning for role selection, which enables robots to learn the role based on the state status from the upper-view. Besides, an intelligent role switching mechanism enables the role selection module to function between two timesteps, promoting both exploration and coverage interchangeably. Then the primitive policy learns how to plan based on their assigned roles and local observation for sub-task execution. The well-designed experiments show the scalability and generalization of our method compared with state-of-the-art approaches in the scenes with varying complexity and number of robots.

cs.RO↗

arXiv2023

Nowhere to Go: Benchmarking Multi-robot Collaboration in Target Trapping Environment

Collaboration is one of the most important factors in multi-robot systems. Considering certain real-world applications and to further promote its development, we propose a new benchmark to evaluate multi-robot collaboration in Target Trapping Environment (T2E). In T2E, two kinds of robots (called captor robot and target robot) share the same space. The captors aim to catch the target collaboratively, while the target will try to escape from the trap. Both the trapping and escaping process can use the environment layout to help achieve the corresponding objective, which requires high collaboration between robots and the utilization of the environment. For the benchmark, we present and evaluate multiple learning-based baselines in T2E, and provide insights into regimes of multi-robot collaboration. We also make our benchmark publicly available and encourage researchers from related robotics disciplines to propose, evaluate, and compare their solutions in this benchmark. Our project is released at https://github.com/Dr-Xiaogaren/T2E.

cs.RO↗

arXiv2021

A General Auxiliary Controller for Multi-agent Flocking

We aim to improve the performance of multi-agent flocking behavior by quantifying the structural significance of each agent. We designed a confidence score(ConfScore) to measure the spatial significance of each agent. The score will be used by an auxiliary controller to refine the velocity of agents. The agents will be enforced to follow the motion of the leader agents whose ConfScores are high. We demonstrate the efficacy of the auxiliary controller by applying it to several existing algorithms including learning-based and non-learning-based methods. Furthermore, we examined how the auxiliary controller can help improve the performance under different settings of communication radius, number of agents and maximum initial velocity.

cs.MA↗

arXiv2021

Mobile Robot Path Planning in Dynamic Environments: A Survey

There are many challenges for robot navigation in densely populated dynamic environments. This paper presents a survey of the path planning methods for robot navigation in dense environments. Particularly, the path planning in the navigation framework of mobile robots is composed of global path planning and local path planning, with regard to the planning scope and the executability. Within this framework, the recent progress of the path planning methods is presented in the paper, while examining their strengths and weaknesses. Notably, the recently developed Velocity Obstacle method and its variants that serve as the local planner are analyzed comprehensively. Moreover, as a model-free method that is widely used in current robot applications, the reinforcement learning-based path planning algorithms are detailed in this paper.

cs.RO↗