Efficient crowd navigation requires anticipating dynamic collision-free space without relying on fragile object tracking. We propose the Don't Risk It Planner (DRIP), an end-to-end LiDAR-only planning framework that couples occupancy forecasting with trajectory-conditioned clearance and uncertainty estimation. Operating directly on LiDAR-derived occupancy grid histories, DRIP predicts a distribution over minimum robot-obstacle clearance for candidate control sequences to evaluate collision risk. The model is trained using a risk cost that grounds predictive uncertainty directly in empirical collision outcomes rather than geometric regression alone. In closed-loop experiments with up to 45 pedestrians, DRIP achieves higher success rates with fewer collisions and reduced freezing behavior compared to state-of-the-art baselines.
Figures & tables
Fig. 2 : Overview of DRIP’s LiDAR-only prediction and trajectory-conditioned risk architecture. A history H of pose-warped BEV occupancy maps is encoded independently by a shared-weight spatial CNN, conditioned on ego velocity V through FiLM. Spatiotemporal Transformer blocks then reason over the temporal history and spatial BEV tokens to produce a shared scene representation zscene . Two branches use this representation: the occupancy decoder predicts the future evolution of the scene ( Ok ) over a 20 -step horizon, while the trajectory-conditioned Distance Head combines scene features with candidate trajectory queries qk to predict a stepwise clearance distribution (μk,σk2) and a trajectory-specific kernel width λ . These predictions are subsequently used to compute the distributional MMD 2 risk rθ(u) for each candidate trajectory u .
TABLE I : Closed-loop navigation performance and sensor noise robustness in the simulated Lobby world with 35 and 45 pedestrians. Higher success rate ( ↑ ) and velocity ( ↑ ) are better; lower completion time ( ↓ ) and path length ( ↓ ) are better. Best and second-best success rates are highlighted. ( † DRL-VO utilizes privileged pedestrian tracking/velocities and is excluded from direct sensor noise testing).
Fig. 3 : Box plot of best-of- K clearance residuals relative to privileged ground truth across dynamic evaluation episodes. The risk-calibrated model (( 18 )) yields a lower median error and narrower spread than the NLL-only baseline without Lrisk , Lhaz ), demonstrating well-calibrated predictive variance that tightly bounds actual obstacle encounters.
Fig. 4 : Visualization of the occupancy forecasting. Top row: The first 5 steps of the predicted future occupancy maps ( Ok ), visualized as thresholded binary maps, taken from the full 20-step planning horizon. Bottom row: The corresponding ground-truth future occupancy maps ( Okgt ). The network successfully anticipates the continuous motion of dynamic obstacles and maintains static boundary structures, closely matching the ground truth without relying on explicit pedestrian tracking.
Safe crowd navigation under distribution shift requires uncertainty representations that capture structured human-motion prediction errors and safety objectives that account for rare but consequential failures. Existing uncertainty-aware methods typically represent prediction errors using isotropic regions, which can be either overly conservative or poorly aligned with directional motion uncertainty. We introduce a risk-aware navigation framework that uses anisotropic conformal ellipsoids to translate structured prediction uncertainty into an episode-level conditional value-at-risk (CVaR) signal that regulates the Lagrangian safety penalty. In particular, adaptive ellipsoidal conformal prediction (AECP) captures directional prediction errors and adaptively calibrates uncertainty regions under distribution shift, while the resulting CVaR-regulated navigation policy is optimized using Lagrangian proximal policy optimization. We evaluate our proposed method under both in-distribution settings and out-of-distribution (OOD) settings involving shifts in pedestrian motion patterns. Compared with state-of-the-art baselines, our method maintains competitive in-distribution performance while improving success rates by 5.68-7.44 percentage points and reducing collision rates by 5.44-6.64 percentage points across OOD settings. We further deploy the trained policy without fine-tuning on a physical robot with onboard perception and CPU-only inference, showing that the full pipeline is feasible in physical crowd navigation.
Ruihan A. Li, Ziyao Guo, Yingying Li
Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL
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.
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