Towards evasive maneuvers with quadrotors using dynamic vision sensors
Authors:
- 1 September 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
We present a method to predict collisions with objects thrown at a quadrotor using a pair of dynamic vision sensors (DVS). Due to the micro-second temporal resolution of these sensors and the sparsity of their output, the object's trajectory can be estimated with minimal latency. Unlike standard cameras that send frames at a fixed frame rate, a DVS only transmits pixel-level brightness changes (“events”) at the time they occur. Our method tracks spherical objects on the image plane using probabilistic trackers that are updated with each incoming event. The object's trajectory is estimated using an Extended Kalman Filter with a mixed state space that allows incorporation of both the object's dynamics and the measurement noise in the image plane. Using error-propagation techniques, we predict a collision if the 3σ-ellipsoid along the predicted trajectory intersects with a safety sphere around the quadrotor. We experimentally demonstrate that our method allows initiating evasive maneuvers early enough to avoid collisions.Keywords
This publication has 22 references indexed in Scilit:
- Asynchronous visual event-based time-to-contactFrontiers in Neuroscience, 2014
- Low-latency localization by active LED markers tracking using a dynamic vision sensor2013
- Event-Based Visual FlowIEEE Transactions on Neural Networks and Learning Systems, 2013
- Event-based 3D reconstruction from neuromorphic retinasNeural Networks, 2013
- Simultaneous Localization and Mapping for Event-Based Vision Systems2013
- Event-based particle filtering for robot self-localization2012
- Asynchronous Event-Based Visual Shape Tracking for Stable Haptic Feedback in MicroroboticsIEEE Transactions on Robotics, 2012
- Live demonstration: Gesture-based remote control using stereo pair of dynamic vision sensors2012
- Asynchronous Event-Based Hebbian Epipolar GeometryIEEE Transactions on Neural Networks, 2011
- A Theory of Visual Control of Braking Based on Information about Time-to-CollisionPerception, 1976