mlsanityData to 7 Oct 2026

Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation

arXiv 2203.15041 ↗First posted 28 Mar 2022cs.RO cs.CV cs.LGcited by 122

On the map: Offline RL and imitation learning from data → Social robot navigation

Abstract (arXiv)

Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a 'socially compliant' manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human populated environments (e.g., domestic service robots in homes and restaurants and food delivery robots on public sidewalks), incorporating socially compliant navigation behaviors on these robots becomes critical to ensuring safe and comfortable human robot coexistence. To address this challenge, imitation learning is a promising framework, since it is easier for humans to demonstrate the task of social navigation rather than to formulate reward functions that accurately capture the complex multi objective setting of social navigation. The use of imitation learning and inverse reinforcement learning to social navigation for mobile robots, however, is currently hindered by a lack of large scale datasets that capture socially compliant robot navigation demonstrations in the wild. To fill this gap, we introduce Socially CompliAnt Navigation Dataset (SCAND) a large scale, first person view dataset of socially compliant navigation demonstrations. Our dataset contains 8.7 hours, 138 trajectories, 25 miles of socially compliant, human teleoperated driving demonstrations that comprises multi modal data streams including 3D lidar, joystick commands, odometry, visual and inertial information, collected on two morphologically different mobile robots a Boston Dynamics Spot and a Clearpath Jackal by four different human demonstrators in both indoor and outdoor environments. We additionally perform preliminary analysis and validation through real world robot experiments and show that navigation policies learned by imitation learning on SCAND generate socially compliant behaviors

Key facts. Cited by 122 papers in the map (data through 7 Oct 2026). Placed in Social robot navigation, one of 13 directions in Offline RL and imitation learning from data. Builds on 20 of its 49 references that are in the map. First posted on arXiv 28 Mar 2022.

Builds on

20 of 49 references.

References · 20

  1. 2016End to End Learning for Self-Driving Carscited by 1,000
  2. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 128
  3. 2019Deep Visual MPC-Policy Learning for Navigationcited by 54
  4. 2017Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learningcited by 50
  5. 2019Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learningcited by 44
  6. 2019TH"OR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Datasetcited by 36
  7. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 35
  8. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigationcited by 27
  9. 2021SocNavBench: A Grounded Simulation Testing Framework for Evaluating Social Navigationcited by 23
  10. 2020SEAN: Social Environment for Autonomous Navigationcited by 18
  11. 2020Reinforced Grounded Action Transformation for Sim-to-Real Transfercited by 17
  12. 2020Stochastic Grounded Action Transformation for Robot Learning in Simulationcited by 16
8 more
  1. 2021APPL: Adaptive Planner Parameter Learningcited by 15
  2. 2021Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environmentscited by 12
  3. 2019SocNav1: A Dataset to Benchmark and Learn Social Navigation Conventionscited by 10
  4. 2021SOCIALGYM: A Framework for Benchmarking Social Robot Navigationcited by 10
  5. 2020An Approach to Deploy Interactive Robotic Simulators on the Web for HRI Experiments: Results in Social Robot Navigationcited by 7
  6. 2021From Agile Ground to Aerial Navigation: Learning from Learned Hallucinationcited by 7
  7. 2020Robot Perception of Static and Dynamic Objects with an Autonomous Floor Scrubbercited by 6
  8. 2021DeepSocNav: Social Navigation by Imitating Human Behaviorscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 11; 2024: 19; 2025: 34; 2026: 49.

122 papers.

Sort:

By area:

  1. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  2. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  3. 2024Navigation World Modelscited by 262
  4. 2023ViNT: A Foundation Model for Visual Navigationcited by 210
  5. 2022GNM: A General Navigation Model to Drive Any Robotcited by 161
  6. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  7. 2023SACSoN: Scalable Autonomous Control for Social Navigationcited by 60
  8. 2023QUAR-VLA: Vision-Language-Action Model for Quadruped Robotscited by 55
  9. 2023Principles and Guidelines for Evaluating Social Robot Navigation Algorithmscited by 52
  10. 2024VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Modelscited by 46
  11. 2025NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidancecited by 46
  12. 2025OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigationcited by 34
38 more
  1. 2026Beyond Language Modeling: An Exploration of Multimodal Pretrainingcited by 32
  2. 2023Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Datasetcited by 28
  3. 2024GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robotcited by 28
  4. 2022Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigationcited by 27
  5. 2022JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Trackingcited by 25
  6. 2025Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Modelscited by 24
  7. 2025NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigationcited by 23
  8. 2025A Survey of Interactive Generative Videocited by 23
  9. 2026ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigationcited by 23
  10. 2024MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Predictioncited by 21
  11. 2022VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamicscited by 19
  12. 2025NaviTrace: Evaluating Embodied Navigation of Vision-Language Modelscited by 13
  13. 2026Walk through Paintings: Egocentric World Models from Internet Priorscited by 13
  14. 2024Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentationcited by 12
  15. 2025Learning to Drive Anywhere with Model-Based Reannotationcited by 12
  16. 2025SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigationcited by 12
  17. 2025TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfercited by 11
  18. 2025From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learningcited by 11
  19. 2025Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresightcited by 11
  20. 2023SANPO: A Scene Understanding, Accessibility and Human Navigation Datasetcited by 10
  21. 2023STERLING: Self-Supervised Terrain Representation Learning from Unconstrained Robot Experiencecited by 10
  22. 2022High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimizationcited by 9
  23. 2024FlowNav: Combining Flow Matching and Depth Priors for Efficient Navigationcited by 9
  24. 2025LookOut: Real-World Humanoid Egocentric Navigationcited by 9
  25. 2026RAE-NWM: Navigation World Model in Dense Visual Representation Spacecited by 9
  26. 2026Language-Conditioned World Modeling for Visual Navigationcited by 9
  27. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 8
  28. 2024DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigationcited by 7
  29. 2026AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edgecited by 7
  30. 2026MWM: Mobile World Models for Action-Conditioned Consistent Predictioncited by 7
  31. 2026NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigationcited by 7
  32. 2022StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networkscited by 6
  33. 2022Exploiting Proximity-Aware Tasks for Embodied Social Navigationcited by 6
  34. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowdscited by 6
  35. 2024GSON: A Group-based Social Navigation Framework with Large Multimodal Modelcited by 6
  36. 2024HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environmentscited by 6
  37. 2025VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigationcited by 6
  38. 2025UrbanNav: Learning Language-Guided Urban Navigation from Web-Scale Human Trajectoriescited by 6

50 most cited of 122 All 122 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Trajectory Learning with Graph Representations for Social Robot Navigation
  2. 2021Sample Efficient Social Navigation Using Inverse Reinforcement Learning
  3. 2024Learning Early Social Maneuvers for Enhanced Social Navigation ↗
  4. 2020NaviGAN: A Generative Approach for Socially Compliant Navigation
  5. 2026SoGuDiff: Socially Guided Diffusion for Steerable, Norm-Grounded Robot Navigation
  6. 2025MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning
  7. 2025Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning
  8. 2022Feedback-efficient Active Preference Learning for Socially Aware Robot Navigation