Organizations: School of Automation, Beijing Institute of Technology, Beijing 100081, China · State Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing 100081, China
Safe robot navigation in dense crowds requires reasoning about pedestrian motion and how it may change in response to a robot. However, many learning-based approaches generate pedestrian motion independently of the robot or assume uniform reciprocity, omitting an important source of interaction uncertainty. This paper presents a Human-Human & Human-Robot Interaction Transformer (H2INT), a reinforcement learning framework that retains robot-conditioned changes in pedestrian motion during policy learning while allowing responsiveness to vary across pedestrians. Responsiveness affects the crowd dynamics when the robot is visible but is not supplied as a policy input; the policy must instead infer its consequences from robot-centered relative positions. A two-stage gated Transformer progressively encodes human-human and human-robot relations, while a recurrent policy captures their temporal evolution. A curriculum gradually reduces pedestrian responsiveness to increase interaction difficulty. Simulation experiments demonstrate improved navigation safety and robustness over representative baselines across response conditions and crowd densities, and show transfer without retraining to structurally distinct crowd-flow layouts. Ablations support the hierarchical relational encoding and gated updates. Real-robot deployment further verifies that the learned policy can operate with sparse observations in a physical environment.
Figures & tables
Fig. 1: An illustration of interaction relationships in crowd navigation.
Fig. 2: Overview of the proposed policy learning framework. The robot and pedestrians are represented by relative spatial edges and embedded into a shared latent space. A two-stage gated Transformer progressively refines the interaction representation, and the resulting context vector is processed by an Actor-Critic policy network for navigation.
Fig. 3: Two-stage gated Transformer encoder. The first stage constructs an interaction representation, and the second refines the encoded relational features for robot decision making.
Fig. 4: Training performance with and without responsiveness annealing. Dashed lines mark reductions of ρresp from 0.8 to 0.0. The annealed policy (blue) converges faster and more stably than the non-annealed baseline (orange); shaded regions denote ± one standard deviation.
Set
Method
rs↑
rc↓
rt↓
ts↓
lp↓
Δv↓
High
ORCA
97
3
0
14.68
18.14
1.00
SF
65
32
3
20.77
21.47
0.99
CADRL
84
13
3
15.12
19.98
1.21
SARL
88
10
2
14.01
19.11
1.15
DS-RNN
91
8
1
16.36
22.23
1.58
AIG-GST
92
6
2
15.77
22.48
1.63
TABLE I: Comparison under Different Response Regimes
Set
Method
rs↑
rc↓
rt↓
ts↓
lp↓
Δv↓
N=10
ORCA
93
7
0
12.14
17.61
1.00
SF
60
40
0
16.31
18.41
1.00
CADRL
85
10
5
13.91
19.50
1.10
SARL
93
7
0
13.10
18.05
1.16
DS-RNN
89
11
0
12.39
18.69
1.04
AIG-GST
95
5
0
14.37
20.48
1.51
TABLE II: Comparison under Different Crowd Scales
Fig. 5: Ablation trends under different pedestrian response regimes and crowd sizes. High, Medium, and Low correspond to mean responsiveness probabilities ρresp of 0.7, 0.5, and 0.3, respectively.
Set
Method
rs↑
rc↓
rt↓
ts↓
lp↓
Δv↓
High
ORCA
93
5
2
17.39
22.16
0.99
SF
56
32
12
23.91
26.04
0.94
CADRL
77
17
6
18.23
24.19
1.25
SARL
85
11
4
16.59
23.51
1.20
DS-RNN
76
16
8
23.57
32.38
1.93
AIG-GST
91
8
1
16.18
25.48
1.62
TABLE III: Comparison in Unseen Crowded Environments
Fig. 6: Navigation trajectories in four crowd layouts. The robot and goal are shown in yellow and red, respectively; red and multicolored dashed curves denote the robot and pedestrian trajectories.
Fig. 7: Snapshots of real-world indoor navigation at successive timesteps. The illustrated run is completed without collision among naturally moving pedestrians.
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 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
Humans often observe others before interacting and adjust their behavior accordingly. Robot navigation in crowds, however, often represents pedestrians mainly by observed geometric states, leaving individual differences in interaction tendencies implicit. We propose PRISM (Predictive Representation of Interaction Style and Motion), a framework that infers interaction traits from passive observations of human-human interactions. PRISM encodes human trajectories into a continuous ordinal latent space with a transformer encoder trained by Rank-N-Contrast loss, and pairs each inferred trait with a temporal-stability score supplied to the navigation policy. In randomized crowd simulations, PRISM reduces collision rates over the geometry-only baseline and yields small improvements in navigation-time and path-length metrics. These results suggest the utility of passive latent-trait inference for social navigation in dynamic crowds.
Bo-Han Chen, Hiromu Taketsugu, Norimichi Ukita
National Chung Hsing University · Toyota Technological Institute
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 K nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with N∈[11,16] pedestrians in a 3m×3m arena and evaluated up to N=21 pedestrians (1.3× denser), our policy reaches the goal in >99% of episodes and achieves 86% collision-free success in random crowds, with markedly less freezing than analytical methods and a >60-point collision-free margin over learning-based benchmark methods. Codes are available at https://github.com/jznmsl/PSS-Social.