Predictive Training with Latent Imagination for Visual Quadruped Navigation

• URL: http://arxiv.org/abs/2607.17574v1
• Date: Mon, 20 Jul 2026 05:33:22 GMT
• Title: Predictive Training with Latent Imagination for Visual Quadruped Navigation
• Abstract summary: Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory.<n>Lightweight predictive supervision applied to the policy's recurrent state during training can encode anticipatory obstacle dynamics without modifying the inference-time controller.<n>On simulated and real-world navigation benchmarks with dynamic obstacles, our method substantially improves navigation success while reducing collision rates through the predictive training signal alone.
• Score: 2.687590979817173
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory, with limited capacity to anticipate how moving obstacles will evolve in the near future. In dynamic environments, this reactivity causes the robot to respond too late because collision risk depends on short-horizon scene structure rather than on current obstacle positions alone. Lightweight predictive supervision applied to the policy's recurrent state during training can encode anticipatory obstacle dynamics without modifying the inference-time controller. We augment a reactive LSTM-SRU navigation backbone with an auxiliary JEPA-style predictor and SIGReg regularization: during training, the predictor supervises the deterministic hidden state to anticipate its own next state; at inference, it is fully discarded, incurring zero additional computational cost. On simulated and real-world navigation benchmarks with dynamic obstacles, our method substantially improves navigation success while reducing collision rates through the predictive training signal alone, without additional inference-time parameters. Real-robot deployment on a Unitree Go2 demonstrates zero-shot sim-to-real transfer: the controller navigates cluttered indoor and dynamic outdoor environments without fine-tuning, with evasive behavior consistent with the collision reduction observed in simulation.

Related papers

• A Task-Space Receding Horizon Controller for Fast Collision Avoidance [0.08594140167290099]
  Real-time collision avoidance for robotic manipulators requires fast reactions to unexpected obstacle motion.<n>Full model predictive control can provide this foresight, but its online cost may grow quickly with horizon length, model fidelity, and the number of active geometric constraints.<n>We present a task-space receding-horizon controller that uses a short contact-consistent rollout to generate a terminal kinematic reference.
  arXiv  Detail & Related papers  (2026-07-17T08:13:12Z)
• Learning Agile Navigation in Crowded Environments for Quadruped Robots [19.29089241882416]
  VOP-Nav is a novel navigation system for quadruped robots.<n>It combines the geometric safety of Velocity Obstacles with the agile adaptability of end-to-end learning.<n>VOP-Nav achieves higher success rates than all baselines while balancing speed and collision avoidance.
  arXiv  Detail & Related papers  (2026-07-16T14:16:19Z)
• KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility [27.73146983499444]
  Deep Reinforcement Learning (DRL) has shown promise for social navigation, yet its real-world deployment remains hindered by a persistent sim-to-real gap.<n>This work presents a unified framework that addresses these limitations to produce dynamically feasible navigation policies.<n> Experiments in real-world environments demonstrate that, when combined with the proposed tracking pipeline, KinematicRL can be deployed on a real differential drive robot with minimal modifications.
  arXiv  Detail & Related papers  (2026-06-10T13:07:03Z)
• Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout [55.19244743715421]
  Driver-WM is a driver-centric latent world model that rolls out in-cabin dynamics causally conditioned on out-cabin traffic context.<n>It unifies physical kinematics forecasting with auxiliary behavioral and emotional semantic recognition.<n>Driver-WM yields robust long-horizon geometric forecasting for reactive high-motion maneuvers.
  arXiv  Detail & Related papers  (2026-05-06T16:30:48Z)
• Physics-Informed Reinforcement Learning of Spatial Density Velocity Potentials for Map-Free Racing [73.88859384645264]
  Out-Of-Distribution (OOD) generalization to various racetracks utilizes Machine Learning (ML) to encode the mathematical relation between sensor data and vehicle actuation for end-to-end control.<n>This paper presents a DRL method that parameterizes nonlinear vehicle dynamics from the spectral distribution of depth measurements with a non-geometric, physics-informed reward, to infer vehicle time-optimal and overtaking racing controls with an Artificial Neural Network (ANN)<n>The policy outperforms human demonstrations by 12% in OOD tracks on proportionally scaled hardware, by maximizing the friction circle with tire dynamics that resemble an empirical Pacejka tire model.
  arXiv  Detail & Related papers  (2026-04-10T17:12:07Z)
• SPOT: Spatio-Temporal Obstacle-free Trajectory Planning for UAVs in an Unknown Dynamic Environment [1.9181913148426697]
  We develop a 4-dimensional planner, integrated with vision-based Safe Flight Corridor (SFC) generation.<n>We validate our method extensively in both simulation and real-world hardware experiments and benchmark it against state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-02-01T12:24:12Z)
• Model Predictive Control for Crowd Navigation via Learning-Based Trajectory Prediction [2.8544513613730214]
  This work evaluates the integration of a deep learning-based Social-Implicit (SI) pedestrian trajectory predictor within a Model Predictive Control (MPC) framework on the physical Continental Corriere robot.<n>Results show that SI improves trajectory prediction - reducing errors by up to 76% in low-density settings - and enhances safety and motion smoothness in crowded scenes.<n>These findings emphasize the importance of system-level evaluation and highlight the SI-MPC framework's promise for safer, more adaptive navigation in dynamic, human-populated environments.
  arXiv  Detail & Related papers  (2025-08-09T19:11:28Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Planning with Adaptive World Models for Autonomous Driving [50.4439896514353]
  We present nuPlan, a real-world motion planning benchmark that captures multi-agent interactions.<n>We learn to model such unique behaviors with BehaviorNet, a graph convolutional neural network (GCNN)<n>We also present AdaptiveDriver, a model-predictive control (MPC) based planner that unrolls different world models conditioned on BehaviorNet's predictions.
  arXiv  Detail & Related papers  (2024-06-15T18:53:45Z)
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning [125.61772424068903]
  Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. We present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents.
  arXiv  Detail & Related papers  (2024-03-09T02:34:13Z)
• Nonprehensile Riemannian Motion Predictive Control [57.295751294224765]
  We introduce a novel Real-to-Sim reward analysis technique to reliably imagine and predict the outcome of taking possible actions for a real robotic platform. We produce a closed-loop controller to reactively push objects in a continuous action space. We observe that RMPC is robust in cluttered as well as occluded environments and outperforms the baselines.
  arXiv  Detail & Related papers  (2021-11-15T18:50:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.