mlsanityData to 7 Oct 2026

DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation

arXiv 2410.10646 ↗First posted 14 Oct 2024cs.RO cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

How can a robot safely navigate around people with complex motion patterns? Deep Reinforcement Learning (DRL) in simulation holds some promise, but much prior work relies on simulators that fail to capture the nuances of real human motion. Thus, we propose Deep Residual Model Predictive Control (DR-MPC) to enable robots to quickly and safely perform DRL from real-world crowd navigation data. By blending MPC with model-free DRL, DR-MPC overcomes the DRL challenges of large data requirements and unsafe initial behavior. DR-MPC is initialized with MPC-based path tracking, and gradually learns to interact more effectively with humans. To further accelerate learning, a safety component estimates out-of-distribution states to guide the robot away from likely collisions. In simulation, we show that DR-MPC substantially outperforms prior work, including traditional DRL and residual DRL models. Hardware experiments show our approach successfully enables a robot to navigate a variety of crowded situations with few errors using less than 4 hours of training data.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

30 of 43 references.

References · 30

  1. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  2. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  3. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  4. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  5. 2016Deep Exploration via Bootstrapped DQNcited by 518
  6. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  7. 2024The Faiss librarycited by 370
  8. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  9. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  10. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 162
  11. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 128
  12. 2022Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigationcited by 122
18 more
  1. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 104
  2. 2019Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environmentscited by 89
  3. 2023Principles and Guidelines for Evaluating Social Robot Navigation Algorithmscited by 52
  4. 2022Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graphcited by 46
  5. 2019Relational Graph Learning for Crowd Navigationcited by 42
  6. 2020Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learningcited by 36
  7. 2019Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gazecited by 27
  8. 2020Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learningcited by 21
  9. 2023SICNav: Safe and Interactive Crowd Navigation using Model Predictive Control and Bilevel Optimizationcited by 14
  10. 2023NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learningcited by 12
  11. 2022Revisiting Discrete Soft Actor-Criticcited by 11
  12. 2023HuNavSim: A ROS 2 Human Navigation Simulator for Benchmarking Human-Aware Robot Navigationcited by 11
  13. 2023DATT: Deep Adaptive Trajectory Tracking for Quadrotor Controlcited by 11
  14. 2021All-in-One: A DRL-based Control Switch Combining State-of-the-art Navigation Plannerscited by 8
  15. 2024Arena 3.0: Advancing Social Navigation in Collaborative and Highly Dynamic Environmentscited by 5
  16. 2022The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigationcited by 4
  17. 2022Learning Social Navigation from Demonstrations with Conditional Neural Processescited by 3
  18. 2023Off the Beaten Track: Laterally Weighted Motion Planning for Local Obstacle Avoidancecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Towards foundational LiDAR world models with efficient latent flow matchingcited by 10
  2. 2025Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handlingcited by 5
  3. 2026From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selectioncited by 5
  4. 2025Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigationcited by 2
  5. 2026RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPCcited by 0
  6. 2026Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigmscited by 0
  7. 2026SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Controlcited by 0