This is a repository of Neuromorphic Navigation survey from Southeast University, Nanjing, China.
It aims to provide a curated collection of resources for researchers and practitioners interested in neuromorphic navigation, including datasets, hardware platforms, and software tools.
If you find this repository helpful, please consider Stars ⭐ or Sharing 👋.
Note
If you find any missing resources, feel free to submit a Pull Request or open an Issue. We're thrilled to collaborate with you on this repository.
BibTeX Citation
@article{zhang2026survey,
author = {Zhang, Youdong and He, Xu and Meng, Xiaolin and et al.},
title = {A Survey on Neuromorphic Navigation: Implementation Resources, Challenges and Perspectives},
journal = {TechRxiv},
year = {2026},
month = {feb},
doi = {10.36227/techrxiv.177040597.75784815/v1},
note = {Preprint}
}🌳 Decision Tree Flowchart
graph TD
%% 定义样式类别
classDef startNode fill:#f9f,stroke:#333,stroke-width:2px;
classDef decisionNode fill:#bbf,stroke:#333,stroke-width:2px;
classDef hardwareNode fill:#ffb,stroke:#333,stroke-width:1px;
classDef softwareNode fill:#bfb,stroke:#333,stroke-width:1px;
classDef repoNode fill:#eee,stroke:#333,stroke-width:1px,stroke-dasharray: 5 5;
%% 主流程起点
A([Start: What is your primary goal?]):::startNode --> B{Hardware Deployment?}:::decisionNode
A --> C{Algorithm & Simulation?}:::decisionNode
%% 硬件分支
B -- Yes --> D[Which Target Platform?]:::hardwareNode
D -- Intel Loihi Series --> H1[(Lava)]:::repoNode
D -- SpiNNaker Series --> H2[(sPyNNaker / PyNN)]:::repoNode
D -- SynSense Speck/Dynap --> H3[(Samna)]:::repoNode
D -- BrainScaleS --> H4[(BrainScaleS OS)]:::repoNode
%% 软件与算法分支
C -- Neuroscience / Bio-plausible --> E[Focus on Local Learning e.g., STDP]:::softwareNode
E --> S1[(Brian 2 / NEST / BindsNET)]:::repoNode
C -- Deep Learning Integration --> F[Preferred Training Method?]:::softwareNode
%% 深度学习训练方法分支
F -- ANN-to-SNN Conversion --> S2[(SNN Toolbox / SpikingJelly)]:::repoNode
F -- Direct Training with Surrogate Gradients --> S3[(snnTorch / Norse / SpikingJelly)]:::repoNode
F -- Both / General Purpose --> S4[(SpikingJelly / snnTorch)]:::repoNode
- ITSC: International Conference on Intelligent Transportation Systems
- ECMR: European Conference on Mobile Robots
- CoRL: Conference on Robot Learning
- SIMPAR: IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots
- ICIP: IEEE International Conference on Image Processing
- SSCI: IEEE Symposium Series on Computational Intelligence
- ICCP: IEEE International Conference on Computational Photography
- [TIP-2022] Asynchronous Spatio-Temporal Memory Network for Continuous Event-Based Object Detection
- [ICCV-2023] Learning Optical Flow from Event Camera with Rendered Dataset
- [TRO-2024] CMax-SLAM: Event-Based Rotational-Motion Bundle Adjustment and SLAM System Using Contrast Maximization
- [CVPR-2024] Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach
- [CVPR-2025] Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event Cameras
| Sensor | Pub. | Paper | Link |
|---|---|---|---|
| DVS | IEEE Journal of Solid-State Circuits-2008 | A 128 × 128 120 dB 15 μs Latency Asynchronous Temporal Contrast Vision Sensor | - |
| ATIS | ISSCC-2010 | A QVGA 143dB dynamic range asynchronous address-event PWM dynamic image sensor with lossless pixel-level video compression | - |
| DAVIS240 | IEEE Journal of Solid-State Circuits-2014 | A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision Sensor | Link |
| DAVIS346 | IEEE Trans. Circuits Syst. II-Express Briefs-2018 | Front and Back Illuminated Dynamic and Active Pixel Vision Sensors Comparison | Link |
| CeleX-V | CVPRW-2019 | Live Demonstration: CeleX-V: A 1M Pixel Multi-Mode Event-Based Sensor | Link |
| Vidar | Engineering-2023 | 1000× Faster Camera and Machine Vision with Ordinary Devices | - |
| Speck | Nat. Commun.-2024 | Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chip | Link |
| Tianmouc | Nature-2024 | A vision chip with complementary pathways for open-world sensing | - |
- AER EAR: A Matched Silicon Cochlea Pair With Address Event Representation Interface [Paper]
- Asynchronous binaural spatial audition sensor with 2 × 64 × 4 channel output [Paper] [Link]
- A 0.5V 55μW 64×2-channel binaural silicon cochlea for event-driven stereo-audio sensing [Paper]
- Neuromorphic acoustic sensing using an adaptive microelectromechanical cochlea with integrated feedback [Paper]
- NeuroTac: A Neuromorphic Optical Tactile Sensor applied to Texture Recognition [Paper]
- A spiking and adapting tactile sensor for neuromorphic applications [Paper]
- An artificial piezotronic synapse for tactile perception [Paper]
- Neuromorphic capacitive tactile sensors inspired by slowly adaptive mechanoreceptors [Paper]
- Neuromorphic antennal sensory system [Paper]
- Analog VLSI Circuit Implementation of an Adaptive Neuromorphic Olfaction Chip [Paper]
- Artificial Olfactory Neuron for an In-Sensor Neuromorphic Nose [Paper]
- A Neuromorphic Electronic Nose Design [Paper]
- A bio-inspired neuromorphic olfaction system for highly sensitive and selective gas sensing at room temperature [Paper]
- Gas localization and tracking using neuromorphic olfactory circuit with coupled sensors and memristive neurons [Paper]
- Neuromorphic olfaction with ultralow-power gas sensors and ovonic threshold switch [Paper]
- NeuroRadar: A Neuromorphic Radar Sensor for Low-Power IoT Systems [Paper]
- RF neuromorphic spiking sensor for smart IoT devices [Paper]
- Neuromorphic Wireless Cognition: Event-Driven Semantic Communications for Remote Inference [Paper]
- Neuromorphic Integrated Sensing and Communications [Paper]
| Chips | Signals | Architecture | On-chip learning | Process (nm) | Neurons / Synapses | Power (mW) | Energy/SOP (pJ) | Software |
|---|---|---|---|---|---|---|---|---|
| Neurogrid | Mixed | Async | No | 180 | 64 K / 100 M | 2700 | 119 | NEF |
| Braindrop | Mixed | Async | Yes | 28 | 4 K / 16 M | N. A. | 0.38 | NEF |
| BrainScaleS | Mixed | Sync | Yes | 180 | 512 / 128 K | N. A. | 100 | BrainScaleS OS |
| BrainScaleS2 | Mixed | Sync | Yes | 65 | 512 / 131 K | ~1000 | N. A. | BrainScaleS OS |
| ROLLS | Mixed | Sync | Yes | 180 | 256 / 64 K | ~5 | N. A. | PyNCS |
| Dynap-SE | Mixed | Async | No | 180 | 1024 / 65 K | ~5 | 260 | Samna |
| Dynap-SE2 | Mixed | Async | Yes | 180 | 1024 / 65 K | N. A. | 150 | Samna |
| Loihi | Digital | Async | Yes | 14 | 128 K / 128 M | ~1000 | 23.6 | Lava |
| Loihi2 | Digital | Async | Yes | 7 | 1 M / 120 M | <50 | N. A. | Lava |
| TrueNorth | Digital | Hybrid async-sync | No | 28 | 1 M / 256 M | ~70 | 26 | Corelet |
| NorthPole | Digital | Sync | No | 12 | N. A. | N. A. | N. A. | Custom |
| SpiNNaker | Digital | GALS | Yes | 130 | 18 K / 18 M | ~1000 | 4000 | PyNN, NEST |
| SpiNNaker2 | Digital | GALS | Yes | 22 | Configuration | ~1000 | 10 | PyNN, NEST |
| Tianjic | Digital | Sync | No | 28 | 40 K / 10 M | ~1000 | 1.54 | LynOS |
| TianjicX | Digital | Hybrid async-sync | Yes | 28 | 160 K / 20 M | ~600 | N. A. | LynOS |
| Darwin | Digital | Sync | No | 180 | 2048 / 4.19 M | 0.84 | N. A. | DarwinOS |
| Darwin2 | Digital | Sync | No | 55 | 147 k / 10 M | ~100 | N. A. | DarwinOS |
| Darwin3 | Digital | GALS | Yes | 22 | 2.3 M / — | N. A. | 5.47 | DarwinOS |
Architecture. Async: Asynchronous; Sync: Synchronous; GALS: Globally Asynchronous Locally Synchronous.
| Software | Year | Programming Language | Paper | Open Resource |
|---|---|---|---|---|
| Gazebo | 2004 | C++, Python | Design and use paradigms for Gazebo, an open-source multi-robot simulator | GitHub |
| DeepMind Lab | 2016 | Python | DeepMind Lab | GitHub |
| AI2-THOR | 2017 | C#, Python | AI2-THOR: An Interactive 3D Environment for Visual AI | GitHub |
| CARLA | 2017 | C++, Python | CARLA: An Open Urban Driving Simulator | GitHub |
| MINOS | 2017 | Python | MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments | - |
| House3D | 2018 | C++, Python | Building Generalizable Agents with a Realistic and Rich 3D Environment | GitHub |
| Habitat | 2019 | Python | Habitat: A Platform for Embodied AI Research | GitHub |
| RoboTHOR | 2020 | Python | RoboTHOR: An Open Simulation-to-Real Embodied AI Platform | GitHub |
| LGSVL | 2020 | C# | LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving | GitHub |
| AirSim | 2020 | Python | AirSim Drone Racing Lab | GitHub |
| Software | Year | Programming Language | Paper | Open Resource |
|---|---|---|---|---|
| NRP | 2017 | Python | Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform | Website |
| Tonic | 2021 | Python | - | GitHub |
| OpenRatSLAM | 2013 | MATLAB, C++, Python | OpenRatSLAM: an open source brain-based SLAM system | Website |
| SpikeCoding | 2022 | MATLAB, Python | A toolbox for neuromorphic perception in robotics | GitHub |
| CARLsim++ | 2025 | C++, Python | An integrated toolbox for creating neuromorphic edge applications | GitHub |
- Open Neuromorphic: https://open-neuromorphic.org/
Open Neuromorphic is a global community dedicated to advancing education, research, and open-source collaboration in brain-inspired AI and neuromorphic computing.
- Intel Neuromorphic Research Community : https://www.intel.com/content/www/us/en/research/neuromorphic-community.html
The Intel Neuromorphic Research Community (Intel NRC) is an ecosystem of academic groups, government labs, research institutions, and companies around the world working with Intel to further neuromorphic computing and develop innovative AI applications.
- NeuroPAC: https://www.neuropac.info/
NeuroPAC was launched in 2021 as an NSF-supported effort under the AccelNet (Accelerating Research through International Network-to-Network Collaborations) program led by the University of Maryland and Johns Hopkins University. Its goal is to network neuromorphic engineers with computational neuroscientists, roboticists, and computational theory and perception researchers to advance the foundations of Neuromorphic Intelligence.
- Neuromorphs: https://neuromorphs.net/
Welcome to the brand new NEUROMORPHS home for all students, researchers, faculty, developers, entrepreneurs and all interested in the field of neuromorphic engineering and computing!
Here are the services available for our community:
- https://forum.neuromorphs.net (Flarum): this is a forum service for the community at large to share general news and results, make announcements and start discussions on topics related to neuromorphic engineering and computing. Here we can share information in smaller sub-groups and teams, but it is nice to have a place where all information is available to all.
- https://mm.neuromorphs.net (MatterMost): this is an open-source messaging service, similar to Slack, for small, focused groups to coordinate projects (such as Telluride or CapoCaccia work-groups), to get quick replies to questions or post announcements relevant to the specific group (e.g., 2025 CapoCaccia Workshop participants)
- https://cloud.neuromorphs.net (NextCloud): this is a cloud-based file and storage server with many additional features such as a shared calendar. Given the limited quota available per user, it is useful only for temporary storage and for sharing working material (code, reports, papers, pictures, etc.)
- https://login.neuromorphs.net (Keykloak): convenient common log-in single-sign-on portal for all neuromorphs.net services.
