# Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?

arXiv: https://arxiv.org/abs/1912.06321 · HTML: https://mlsanity.com/paper/1912.06321/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2019.

## Built on by (most cited first, 26 of 26)

- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [Scaling Data Generation in Vision-and-Language Navigation](https://mlsanity.com/paper/2307.15644/) (2023)
- [HomeRobot: Open-Vocabulary Mobile Manipulation](https://mlsanity.com/paper/2306.11565/) (2023)
- [Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2204.09667/) (2022)
- [RobustNav: Towards Benchmarking Robustness in Embodied Navigation](https://mlsanity.com/paper/2106.04531/) (2021)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation](https://mlsanity.com/paper/2105.07593/) (2021)
- [Emergence of Maps in the Memories of Blind Navigation Agents](https://mlsanity.com/paper/2301.13261/) (2023)
- [A Survey on Human-aware Robot Navigation](https://mlsanity.com/paper/2106.11650/) (2021)
- [Success Weighted by Completion Time: A Dynamics-Aware Evaluation Criteria for Embodied Navigation](https://mlsanity.com/paper/2103.08022/) (2021)
- [Human-centric Relation Segmentation: Dataset and Solution](https://mlsanity.com/paper/2105.11168/) (2021)
- [Modality-invariant Visual Odometry for Embodied Vision](https://mlsanity.com/paper/2305.00348/) (2023)
- [Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction](https://mlsanity.com/paper/2306.03857/) (2023)
- [A Step Towards Efficient Evaluation of Complex Perception Tasks in Simulation](https://mlsanity.com/paper/2110.02739/) (2021)
- [DISCO: Embodied Navigation and Interaction via Differentiable Scene Semantics and Dual-level Control](https://mlsanity.com/paper/2407.14758/) (2024)
- [SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation](https://mlsanity.com/paper/2110.07171/) (2021)
- [Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency](https://mlsanity.com/paper/2110.07184/) (2021)
- [MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents](https://mlsanity.com/paper/2211.15992/) (2022)
- [Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation](https://mlsanity.com/paper/2202.01069/) (2022)
- [Attacking Motion Planners Using Adversarial Perception Errors](https://mlsanity.com/paper/2311.12722/) (2023)
- [On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents](https://mlsanity.com/paper/2109.14516/) (2021)
- [Space Processor Computation Time Analysis for Reinforcement Learning and Run Time Assurance Control Policies](https://mlsanity.com/paper/2405.06771/) (2024)
- [RVN-Bench: A Benchmark for Reactive Visual Navigation](https://mlsanity.com/paper/2603.03953/) (2026)

## Abstract (arXiv)

Does progress in simulation translate to progress on robots? If one method outperforms another in simulation, how likely is that trend to hold in reality on a robot? We examine this question for embodied PointGoal navigation, developing engineering tools and a research paradigm for evaluating a simulator by its sim2real predictivity. First, we develop Habitat-PyRobot Bridge (HaPy), a library for seamless execution of identical code on simulated agents and robots, transferring simulation-trained agents to a LoCoBot platform with a one-line code change. Second, we investigate the sim2real predictivity of Habitat-Sim for PointGoal navigation. We 3D-scan a physical lab space to create a virtualized replica, and run parallel tests of 9 different models in reality and simulation. We present a new metric called Sim-vs-Real Correlation Coefficient (SRCC) to quantify predictivity. We find that SRCC for Habitat as used for the CVPR19 challenge is low (0.18 for the success metric), suggesting that performance differences in this simulator-based challenge do not persist after physical deployment. This gap is largely due to AI agents learning to exploit simulator imperfections, abusing collision dynamics to 'slide' along walls, leading to shortcuts through otherwise non-navigable space. Naturally, such exploits do not work in the real world. Our experiments show that it is possible to tune simulation parameters to improve sim2real predictivity (e.g. improving SRCCSucc from 0.18 to 0.844), increasing confidence that in-simulation comparisons will translate to deployed systems in reality.