mlsanityData to 14 Oct 2026

KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility

arXiv 2606.12042 ↗First posted 10 Jun 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Deep Reinforcement Learning (DRL) has shown promise for social navigation, yet its real-world deployment remains hindered by a persistent sim-to-real gap arising from simplified first-order dynamics and context-specific human state estimation pipelines. This work presents a unified framework that addresses these limitations to produce dynamically feasible navigation policies suitable for real-world deployment. First, theoretical analysis reveals that tracking error between simulated and actual robot position decays exponentially with increased control order, motivating the use of higher-order control inputs as DRL action space. A second-order control formulation tailored to differential drive robots is developed, complemented by a stochastic iterative Linear Quadratic Regulator (iLQR) that pretrains the policy via a divergence minimization objective. Second, to avoid the added system complexity of camera-LiDAR fusion, a cluster-based human tracking pipeline using only 2D LiDAR is introduced. Human detections are associated according to both spatial proximity and velocity similarity, enabling reliable differentiation of nearby pedestrians and yielding stable velocity estimates through temporal aggregation. Third, we introduce an unbiased residual gating block to balance reaction- and memory-based behaviors while handling time-varying crowd sizes, both critical for social navigation. The resulting policy, KinematicRL, consistently improves kinematic performance and adapts to varying number of detected humans. 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 32 of its 51 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

32 of 51 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  7. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 910
  8. 2016Simple Online and Realtime Trackingcited by 868
  9. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  10. 2019Stabilizing Transformers for Reinforcement Learningcited by 270
  11. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 190
  12. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
20 more
  1. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 136
  2. 2019Imitation Learning as f-Divergence Minimizationcited by 123
  3. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 118
  4. 2018Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learningcited by 111
  5. 2020Sim-to-Real Transfer for Vision-and-Language Navigationcited by 89
  6. 2021Understanding Domain Randomization for Sim-to-real Transfercited by 80
  7. 2024Agile But Safe: Learning Collision-Free High-Speed Legged Locomotioncited by 73
  8. 2022Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graphcited by 53
  9. 2019Combining Optimal Control and Learning for Visual Navigation in Novel Environmentscited by 52
  10. 2021Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrianscited by 28
  11. 2021Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learningcited by 26
  12. 2023Q-DETR: An Efficient Low-Bit Quantized Detection Transformercited by 24
  13. 2020DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Datacited by 19
  14. 2023Multi-Robot Cooperative Socially-Aware Navigation Using Multi-Agent Reinforcement Learningcited by 17
  15. 2020Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation in Dense Mobile Crowdscited by 16
  16. 2020APPLR: Adaptive Planner Parameter Learning from Reinforcementcited by 16
  17. 2023Control Barrier Functions in Dynamic UAVs for Kinematic Obstacle Avoidance: A Collision Cone Approachcited by 8
  18. 2020Fast-Tracker: A Robust Aerial System for Tracking Agile Target in Cluttered Environmentscited by 5
  19. 2025Safe Navigation in Uncertain Crowded Environments Using Risk Adaptive CVaR Barrier Functionscited by 2
  20. 2023Safety-Critical Control of Nonholonomic Vehicles in Dynamic Environments using Velocity Obstaclescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches
  2. 2026Performance-Preserving Online Adaptation in Social Navigation via Diffusion Steering
  3. 2026End-to-End Safe Social Navigation via Multi-Task Reinforcement Learning and Probabilistic Perception
  4. 2024Socially Integrated Navigation: A Social Acting Robot with Deep Reinforcement Learning
  5. 2026Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation
  6. 2024DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation
  7. 2024Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation
  8. 2024Context-aware Mamba-based Reinforcement Learning for social robot navigation