MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots
Not on the map. Why?
Abstract (arXiv)
Navigation using a monocular camera is pivotal for autonomous operation on tiny aerial robots due to their perfect balance of versatility, cost and accuracy. In this paper, we introduce MinNav, a navigation stack based on optical flow and its uncertainty to fly through a scene with static and dynamic obstacles and unknown-shaped gaps without any prior knowledge of the scene components and/or their locations/ordering. We further improve success rate by using the activeness of the robot to move around in an exploratory way to find obstacles and navigate. We successfully evaluate and demonstrate the proposed approach in many real-world experiments in various environments with static and dynamic obstacles and unknown-shaped gaps with an overall success rate of 70%. To the best of our knowledge, this is the first solution to tackle all the aforementioned navigation cases without prior knowledge using a monocular camera. Our approach is on par in performance with depth based methods with factors of magnitude less computation required and can readily run onboard tiny aerial robots. The accompanying video, supplementary material, code and dataset can be found at https://pear.wpi.edu/research/minnav.html
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 5 Jun 2026.
Builds on
27 of 54 references.
References · 27
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2021Vision Transformers for Dense Predictioncited by 1,789
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
- 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
- 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 421
- 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
- 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 173
- 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
- 2016Revisiting Active Perceptioncited by 90
- 2023Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learningcited by 72
- 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
15 more
- 2019EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Camerascited by 46
- 2019Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenescited by 29
- 2023Autonomous Drone Racing: A Surveycited by 29
- 2023Learning to Fly in Secondscited by 18
- 2021EVPropNet: Detecting Drones By Finding Propellers For Mid-Air Landing And Followingcited by 17
- 2020Neuromorphic control for optic-flow-based landings of MAVs using the Loihi processorcited by 12
- 2022NanoFlowNet: Real-time Dense Optical Flow on a Nano Quadcoptercited by 10
- 2023End-to-end Neural Network Based Quadcopter controlcited by 9
- 2018GapFlyt: Active Vision Based Minimalist Structure-less Gap Detection For Quadrotor Flightcited by 6
- 2020MorphEyes: Variable Baseline Stereo For Quadrotor Navigationcited by 6
- 2021NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interactioncited by 5
- 2022WorldGen: A Large Scale Generative Simulatorcited by 4
- 2023AvoidBench: A high-fidelity vision-based obstacle avoidance benchmarking suite for multi-rotorscited by 4
- 2023Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robotscited by 2
- 2024EdgeFlowNet: 100FPS@1W Dense Optical Flow For Tiny Mobile Robotscited by 1
Built on by
Not cited yet.