cs.LGAug 27, 2026

Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigation

Authors: Wendong Li, Jochen Garcke

Organizations: Institute for Numerical Simulation University of Bonn Bonn, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Robot crowd navigation requires safe and efficient decision-making under dense, dynamic, and multimodal human--robot interactions. Existing reinforcement-learning methods typically output a single reactive action at each timestep, which limits their ability to represent diverse short-term avoidance strategies. We propose Planning Diffusion Policy Optimization (PDPO), an offline-to-online reinforcement-learning framework that uses a diffusion policy to generate short-horizon action chunks for crowd navigation. PDPO is first pretrained on collision-avoidance demonstrations and then fine-tuned online with PPO by treating the denoising process as an internal decision process. During execution, the policy generates a five-step action chunk and applies it in a receding-horizon manner. Furthermore, we observe an evaluation artifact in common crowd-navigation benchmarks: without explicit boundary constraints, learned agents may leave the valid domain and bypass dense crowds. To address this, we introduce a setting in which boundary violations are treated as collisions. Experiments show that PDPO obtains an improved success rate over strong baselines, and ablations demonstrate that action chunks are especially important for the modified bounded benchmark.

Figures & tables

MethodSR ↑\uparrowNT ↓\downarrowPL ↓\downarrowITR ↓\downarrowSD ↑\uparrow
ORCA69.014.7717.6719.610.38
CrowdNav++ (Const. Vel.)87.014.0320.147.000.42
PDPO w/o action chunk86.214.5919.208.040.40
PDPO (Ours)90.614.5020.257.220.41
Table 1: Navigation performance on the original CrowdNav++ benchmark without explicit boundary constraints. ORCA and CrowdNav++ results are reported from [ 7 ] .
MethodSR ↑\uparrowNT ↓\downarrowPL ↓\downarrowITR ↓\downarrowSD ↑\uparrow
ORCA47.021.2617.141.350.50
CrowdNav++ (Const. Vel.)74.5 ±\pm 2.113.35 ±\pm 1.1318.42 ±\pm 0.658.53 ±\pm 0.300.42
PDPO w/o action chunk73.7±0.773.7\pm 0.713.05±0.4613.05\pm 0.4620.93±0.5020.93\pm 0.507.21±0.747.21\pm 0.740.400.40
PDPO (Ours)84.7±1.484.7\pm 1.410.92±0.0410.92\pm 0.0420.58±0.1920.58\pm 0.196.81±0.046.81\pm 0.040.410.41
Table 2: Navigation performance on Bounded CrowdNav . All learning-based methods are trained and evaluated under the same bounded environment, where learning-based methods are evaluated over three random seeds for training the model. ORCA is deterministic and reported without standard deviation. The standard deviation for SD is negligible for all approaches.
Figure 1: Representative snapshots of action chunks generated by PDPO during navigation through a dense crowd. In each snapshot, the dashed circle denotes the robot’s observation range, blue dots denote humans with predicted linear trajectories, the green dot denotes the robot, and the red cross the end of the action chunk. The generated chunks provide coherent short-horizon local plans that adapt to nearby pedestrians. Complete storyboards and multimodal samples are in Appendix C .
Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

HyperparameterValue
Workspace size12×12 m212\times 12~\mathrm{m}^{2}
Number of humans20
Robot radius0.2 m0.2~\mathrm{m}
Robot maximum speed1.0 m/s1.0~\mathrm{m/s}
Robot sensing range6.0 m6.0~\mathrm{m}
Control interval0.25 s0.25~\mathrm{s}
Appendix
Table 3: Environment settings, network architecture, diffusion-model settings, and training hyperparameters.
MethodTrainable Parameters
CrowdNav++ (Const. Vel.)2.5032.503 M
PDPO (Ours)1.0491.049 M
Appendix
Table 4: Trainable parameter count of learning-based methods.
Figure 2: Online fine-tuning curves of PDPO and its ablation on Bounded CrowdNav over the common training horizon. Left: training success rate. Right: average training reward.
Figure 3: Complete storyboard of a PDPO trajectory from step 60 to step 68. The generated action chunks remain coherent while adapting to nearby pedestrians.
Figure 4: Complete storyboard of multimodal action chunks generated by PDPO. Multiple sampled short-horizon trajectories are visualized under the same observation, illustrating diverse feasible local plans.
More in this topic

Robot Navigation

Robot navigation studies how robots perceive, localize, plan, and move safely toward goals in static or changing environments.

See all 549 papers

Explore similar work

CardsList
Mar 6, 2026

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variable-density navigation that attains zero-shot density generalization using a density-invariant observation encoding with density-randomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted KK nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with N ⁣∈ ⁣[11,16]N\!\in\![11,16] pedestrians in a 3m×3m3\mathrm{m}\times3\mathrm{m} arena and evaluated up to N ⁣= ⁣21N\!=\!21 pedestrians (1.3×1.3\times denser), our policy reaches the goal in >99%>99\% of episodes and achieves 86%86\% collision-free success in random crowds, with markedly less freezing than analytical methods and a > ⁣60>\!60-point collision-free margin over learning-based benchmark methods. Codes are available at https://github.com/jznmsl/PSS-Social.

Jiefu Zhang, Yang Xu, Vaneet Aggarwal

Purdue University, USA

Safe Robot NavigationRobot NavigationRobot Collision AvoidanceRobot Policy LearningRobot Policy Generalization
AskPDF
Jun 24, 2026

Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations

Robot crowd navigation requires the ability to infer human intentions while accounting for the structural constraints of the environment. Currently, deep reinforcement learning (DRL) provides a promising method for learning navigation policies that understand human intentions. However, most of them rely on limited scene representations, treating pedestrians as simple 2D points and ignoring rich visual cues from both humans and the environment. To address this issue, we introduce iCrowdNav, a novel visual crowd navigation method with intention-aware scene representations, to encode behavioral and structural context from egocentric visual observations. Our method employs two key components: a spatio-temporal encoder for extracting occupancy features of the scene, and Intent-Interact Former (I2^2 Former), an attention-based module that encodes human poses to infer pedestrians' motion intentions. These features are integrated into a compact state embedding that supports effective DRL policy training. Extensive experiments show that our method achieves superior performance over baselines, and real-world deployment demonstrates vision-based crowd navigation.

Han Bao, Bingyi Xia, Hanjing Ye +5

Shenzhen Key Laboratory of Robotics Perception and Intelligence, Department of Electronic and Electrical Engineering, SUSTech, Shenzhen, China · Xiamen Key Laboratory of Visual Perception Technology and Application, and the Algorithm Research Center at Reconova Information Technology Co., Ltd. in Xiamen, China · Research Institute of MA&EI, Peng Cheng Laboratory, Shenzhen, China +1

Pedestrian Intention PredictionRobot NavigationRobotic RLSocial Robot NavigationVision-Based Robot Control
AskPDF
Aug 7, 2026

CoCoNav: Conformal Control for Safe Robot Navigation in Crowds

Safe and efficient robot navigation in crowds requires anticipating pedestrian motion despite uncertain and potentially shifting prediction errors. Existing reactive methods can produce oscillatory behavior, while predictive planners often treat forecasts as exact or rely on restrictive error models. Incorporating conservative uncertainty sets as hard constraints can also render model predictive control (MPC) infeasible. We propose CoCoNav, a crowd-navigation framework that combines online conformal calibration with runtime-certified planning. A horizon-specific conformal proportional--integral controller adapts trajectory-error bounds to regulate long-run empirical coverage, enabling the framework to respond to changing prediction errors. A relax-then-verify planner preserves solver feasibility by generating nominal trajectories with soft-constrained MPC and separately certifying them, together with contingency maneuvers, against the calibrated bounds before execution. Simulations and quadruped experiments show that CoCoNav achieves a favorable balance among collision avoidance, task success, and navigation efficiency relative to the evaluated baselines.

Cheng Guo, Mingzhe Ni, Zheng Liang +5

Department of Computer Science, The University of Manchester, Manchester, UK. · Human-Robot Interfaces and Interaction Laboratory, Italian Institute of Technology, Genoa, Italy. · Genisom AI, Shanghai, China. +3

Constrained Motion PlanningConformal PredictionSafe Robot NavigationSocial Robot NavigationRobot SafetyModel Predictive Control+1
AskPDF