mlsanityData to 7 Oct 2026

Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning

arXiv 2501.06946 ↗First posted 12 Jan 2025cs.ROcited by 3

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

Abstract (arXiv)

This paper reports on learning a reward map for social navigation in dynamic environments where the robot can reason about its path at any time, given agents' trajectories and scene geometry. Humans navigating in dense and dynamic indoor environments often work with several implied social rules. A rule-based approach fails to model all possible interactions between humans, robots, and scenes. We propose a novel Smooth Maximum Entropy Deep Inverse Reinforcement Learning (S-MEDIRL) algorithm that can extrapolate beyond expert demos to better encode scene navigability from few-shot demonstrations. The agent learns to predict the cost maps reasoning on trajectory data and scene geometry. The agent samples a trajectory that is then executed using a local crowd navigation controller. We present results in a photo-realistic simulation environment, with a robot and a human navigating a narrow crossing scenario. The robot implicitly learns to exhibit social behaviors such as yielding to oncoming traffic and avoiding deadlocks. We compare the proposed approach to the popular model-based crowd navigation algorithm ORCA and a rule-based agent that exhibits yielding.

Key facts. Cited by 3 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 27 of its 47 references that are in the map. First posted on arXiv 12 Jan 2025.

Builds on

27 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning16 Sep

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  5. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  6. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  7. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
  8. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  9. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  10. 2015Maximum Entropy Deep Inverse Reinforcement Learningcited by 173
  11. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 162
  12. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 128
14 more
  1. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 104
  2. 2021Core Challenges of Social Robot Navigation: A Surveycited by 97
  3. 2020Trajectory Forecasts in Unknown Environments Conditioned on Grid-Based Planscited by 72
  4. 2020Active Preference-Based Gaussian Process Regression for Reward Learningcited by 70
  5. 2019MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement Learningcited by 29
  6. 2021GridToPix: Training Embodied Agents with Minimal Supervisioncited by 20
  7. 2022Spatiotemporal Costmap Inference for MPC via Deep Inverse Reinforcement Learningcited by 10
  8. 2022A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewardscited by 10
  9. 2021Deep Social Forcecited by 8
  10. 2022Feedback-efficient Active Preference Learning for Socially Aware Robot Navigationcited by 6
  11. 2022Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learningcited by 4
  12. 2023DS-MPEPC: Safe and Deadlock-Avoiding Robot Navigation in Cluttered Dynamic Scenescited by 3
  13. 2022Providers-Clients-Robots: Framework for spatial-semantic planning for shared understanding in human-robot interactioncited by 2
  14. 2023Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Probing Prompt Design for Socially Compliant Robot Navigation with Vision Language Modelscited by 1
  2. 2026AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Modelscited by 0
  3. 2026Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigmscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Sample Efficient Social Navigation Using Inverse Reinforcement Learning
  2. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds
  3. 2024Evaluating MEDIRL: A Replication and Ablation Study of Maximum Entropy Deep Inverse Reinforcement Learning for Human Social Navigation
  4. 2020NaviGAN: A Generative Approach for Socially Compliant Navigation
  5. 2026Trajectory Learning with Graph Representations for Social Robot Navigation
  6. 2026Towards Socially Compliant Navigation in Deep Reinforcement Learning via Proxemics-Based Reward Modeling
  7. 2022Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation
  8. 2025COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning