Towards flapping wing robot visual perception: Opportunities and challenges
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 335-343
Abstract
The development of perception systems for bio-inspired flapping wing robots, or ornithopters, is very challenging due to their fast flying maneuvers and the high amount of vibrations and motion blur originated by the wing flapping. Visual sensors have been widely used in aerial robot perception due to their size, weight, and energy consumption capabilities. This paper analyzes the issues and challenges for vision sensors onboard ornithopter robots. Two visual sensors are evaluated: a monocular camera and an event-based camera. First, the pros and cons of integrating different sensors on flapping wing robots are studied. Second, the paper experimentally evaluates the impact of wing flapping frequency on both sensors using experiments with the ornithopter developed in the EU-funded GRIFFIN ERC project.Keywords
This publication has 19 references indexed in Scilit:
- Long-range GPS-denied aerial inertial navigation with LIDAR localization2016
- Autonomous Exploration for Infrastructure Modeling with a Micro Aerial Vehicle2016
- The DelFly2016
- A Machine Learning Approach to Visual Perception of Forest Trails for Mobile RobotsIEEE Robotics and Automation Letters, 2015
- A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision SensorIEEE Journal of Solid-State Circuits, 2014
- Low-latency event-based visual odometry2014
- Altitude feedback control of a flapping-wing microrobot using an on-board biologically inspired optical flow sensor2012
- Mapping the world in 3DNature Photonics, 2010
- The First Takeoff of a Biologically Inspired At-Scale Robotic InsectIEEE Transactions on Robotics, 2008
- Control and perception techniques for aerial roboticsAnnual Reviews in Control, 2004