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

arXiv: https://arxiv.org/abs/2410.10646 · HTML: https://mlsanity.com/paper/2410.10646/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 30 of 30)

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation](https://mlsanity.com/paper/2203.15041/) (2022)
- [Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.07845/) (2016)
- [Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments](https://mlsanity.com/paper/1910.14442/) (2019)
- [Principles and Guidelines for Evaluating Social Robot Navigation Algorithms](https://mlsanity.com/paper/2306.16740/) (2023)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Relational Graph Learning for Crowd Navigation](https://mlsanity.com/paper/1909.13165/) (2019)
- [Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2011.04820/) (2020)
- [Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze](https://mlsanity.com/paper/1909.10400/) (2019)
- [Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning](https://mlsanity.com/paper/2001.06627/) (2020)
- [DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control](https://mlsanity.com/paper/2310.09053/) (2023)
- [SICNav: Safe and Interactive Crowd Navigation using Model Predictive Control and Bilevel Optimization](https://mlsanity.com/paper/2310.10982/) (2023)
- [Revisiting Discrete Soft Actor-Critic](https://mlsanity.com/paper/2209.10081/) (2022)
- [NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning](https://mlsanity.com/paper/2304.05979/) (2023)
- [HuNavSim: A ROS 2 Human Navigation Simulator for Benchmarking Human-Aware Robot Navigation](https://mlsanity.com/paper/2305.01303/) (2023)
- [All-in-One: A DRL-based Control Switch Combining State-of-the-art Navigation Planners](https://mlsanity.com/paper/2109.11636/) (2021)
- [The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigation](https://mlsanity.com/paper/2208.12602/) (2022)
- [Arena 3.0: Advancing Social Navigation in Collaborative and Highly Dynamic Environments](https://mlsanity.com/paper/2406.00837/) (2024)
- [Learning Social Navigation from Demonstrations with Conditional Neural Processes](https://mlsanity.com/paper/2210.03582/) (2022)
- [Off the Beaten Track: Laterally Weighted Motion Planning for Local Obstacle Avoidance](https://mlsanity.com/paper/2309.09334/) (2023)

## Built on by (most cited first, 9 of 9)

- [Towards foundational LiDAR world models with efficient latent flow matching](https://mlsanity.com/paper/2506.23434/) (2025)
- [Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling](https://mlsanity.com/paper/2508.05634/) (2025)
- [From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection](https://mlsanity.com/paper/2602.09002/) (2026)
- [Ratatouille: Imitation Learning Ingredients for Real-world Social Robot Navigation](https://mlsanity.com/paper/2509.17204/) (2025)
- [DiffCVaR: Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions](https://mlsanity.com/paper/2605.21257/) (2026)
- [RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC](https://mlsanity.com/paper/2604.27450/) (2026)
- [Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms](https://mlsanity.com/paper/2608.00625/) (2026)
- [SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control](https://mlsanity.com/paper/2608.21175/) (2026)
- [Performance-Preserving Online Adaptation in Social Navigation via Diffusion Steering](https://mlsanity.com/paper/2609.24317/) (2026)

## 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.