Jihua Dou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jihua Dou has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Huachuan Wang
Harbin Engineering University
2 shared publications - Jianxin Lin
Qingdao Innovation and Development Center of Harbin Engineering University, Qingdao, China
2 shared publications - Kunpeng Ouyang
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
2 shared publications - Weihao Xia
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
1 shared publication - Yuanhao Wang
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
1 shared publication - Zefei Wu
College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin 150001, China
1 shared publication
Latest Publications
- Open Access
- 8 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4828
Risk-Aware Distributional Reinforcement Learning for Safe Path Planning of Surface Sensing Agents
In spatially constrained water domains, surface sensing agents(SSAs) must achieve safe path planning, uncertain currents, and sensor noise. We present a decentralized motion planning and collision-avoidance framework based on distributional reinforcement learning (DRL) that models the full return distribution to enable risk-aware decision making. Each surface sensing agent autonomously proceeds to its designated coordinates without rigid spatial constraints, coordinating implicitly through learned policies and a lightweight safety shield that enforces separation and kinematic limits. The method integrates (i) distributional value estimation for controllable risk sensitivity near hazards, (ii) domain randomization of sea states and disturbances for robustness, and (iii) a shielded action layer compatible with standard reactive rules (e.g., velocity obstacle-style constraints) to guarantee feasible maneuvers. In simulations across cluttered maps and stochastic current fields, the proposed approach improves success rates and reduces near-miss events compared to non-distributional RL and classical planners, while maintaining competitive path length and computation time. The results indicate that DRL-based surface sensing agent navigation is a practical path toward safe, efficient environmental monitoring and surveying.
- 8 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4828
Open AccessRisk-Aware Distributional Reinforcement Learning for Safe Path Planning of Surface Sensing Agents
In spatially constrained water domains, surface sensing agents(SSAs) must achieve safe path planning, uncertain currents, and sensor noise. We present a decentralized motion planning and collision-avoidance framework based on distributional reinforcement learning (DRL) that models the full return distribution to enable risk-aware decision making. Each surface sensing agent autonomously proceeds to its designated coordinates without rigid spatial constraints, coordinating implicitly through learned policies and a lightweight safety shield that enforces separation and kinematic limits. The method integrates (i) distributional value estimation for controllable risk sensitivity near hazards, (ii) domain randomization of sea states and disturbances for robustness, and (iii) a shielded action layer compatible with standard reactive rules (e.g., velocity obstacle-style constraints) to guarantee feasible maneuvers. In simulations across cluttered maps and stochastic current fields, the proposed approach improves success rates and reduces near-miss events compared to non-distributional RL and classical planners, while maintaining competitive path length and computation time. The results indicate that DRL-based surface sensing agent navigation is a practical path toward safe, efficient environmental monitoring and surveying.
- Open Access
From Invariance to Symmetry Breaking in FIM-Aware Cooperative Heterogeneous Agent Networks
We recast cooperative localization and scheduling in heterogeneous multi-agent systems through the lens of symmetry and symmetry breaking. On the geometric side, the Fisher Information Matrix (FIM) objective is invariant to rigid Euclidean transformations of the global frame, while its maximization admits symmetric optimal sensor formations; on the algorithmic side, heterogeneity and task constraints break permutation symmetry across agents, requiring policies that are sensitive to role asymmetries. We model communication as a random graph and quantify structural symmetry via topology metrics (average path length, clustering, betweenness) and graph automorphism-related indices, connecting these to estimation uncertainty. We then design a hybrid reward for reinforcement learning (RL) that is equivariant to agent relabeling within roles yet intentionally introduces asymmetry through distance/FIM terms to avoid degenerate symmetric configurations with poor observability. Simulations show that (i) symmetry-aware, FIM-optimized path planning reduces localization error versus symmetric but non-informative placements; and (ii) controlled symmetry breaking in policy learning improves robustness and data rate–reward trade-offs over baselines. Our results position symmetry/asymmetry as first-class design principles that unify estimation-theoretic invariances with learning-based coordination in complex heterogeneous networks. Under DDPG training, the total data rate (SDR) reaches and the average reward per step (ARPS) is , representing improvements of approximately over the baseline and over SAC , respectively. The network’s mean shortest-path length is , and the average betweenness centrality of the coordination nodes is ≈0.098. Moreover, the FIM-optimized path-planning strategy achieves the lowest localization error among all evaluated policies.Open AccessFrom Invariance to Symmetry Breaking in FIM-Aware Cooperative Heterogeneous Agent Networks
We recast cooperative localization and scheduling in heterogeneous multi-agent systems through the lens of symmetry and symmetry breaking. On the geometric side, the Fisher Information Matrix (FIM) objective is invariant to rigid Euclidean transformations of the global frame, while its maximization admits symmetric optimal sensor formations; on the algorithmic side, heterogeneity and task constraints break permutation symmetry across agents, requiring policies that are sensitive to role asymmetries. We model communication as a random graph and quantify structural symmetry via topology metrics (average path length, clustering, betweenness) and graph automorphism-related indices, connecting these to estimation uncertainty. We then design a hybrid reward for reinforcement learning (RL) that is equivariant to agent relabeling within roles yet intentionally introduces asymmetry through distance/FIM terms to avoid degenerate symmetric configurations with poor observability. Simulations show that (i) symmetry-aware, FIM-optimized path planning reduces localization error versus symmetric but non-informative placements; and (ii) controlled symmetry breaking in policy learning improves robustness and data rate–reward trade-offs over baselines. Our results position symmetry/asymmetry as first-class design principles that unify estimation-theoretic invariances with learning-based coordination in complex heterogeneous networks. Under DDPG training, the total data rate (SDR) reaches and the average reward per step (ARPS) is , representing improvements of approximately over the baseline and over SAC , respectively. The network’s mean shortest-path length is , and the average betweenness centrality of the coordination nodes is ≈0.098. Moreover, the FIM-optimized path-planning strategy achieves the lowest localization error among all evaluated policies.