Rapid, Dynamic Obstacle Avoidance with an Event-based Camera
In this work, we study the effects that perception latency has on the maximum speed a robot can reach to safely navigate through an unknown cluttered environment. We provide a general analysis that can serve as a baseline for future quantitative reasoning for design trade-offs in autonomous robot navigation. We consider the case where the robot is modeled as a linear second-order system with bounded input and navigates through static obstacles. Also, we focus on a scenario where the robot wants to reach a target destination in as little time as possible, and therefore cannot change its longitudinal velocity to avoid obstacles. We show how the maximum latency that the robot can tolerate to guarantee safety is related to the desired speed, the range of its sensing pipeline, and the actuation limitations of the platform (i.e., the maximum acceleration it can produce). As a particular case study, we compare monocular and stereo frame-based cameras against novel, low-latency sensors, such as event cameras, in the case of quadrotor flight. To validate our analysis, we conduct experiments on a quadrotor platform equipped with an event camera to detect and avoid obstacles thrown towards the robot. To the best of our knowledge, this is the first theoretical work in which perception and actuation limitations are jointly considered to study the performance of a robotic platform in high-speed navigation.
Reference:
D. Falanga, S. Kim, D. Scaramuzza, "How Fast is Too Fast? The Role of Perception Latency in High-Speed Sense and Avoid", IEEE Robotics and Automation Letters (RA-L), 2019.
PDF: http://rpg.ifi.uzh.ch/docs/RAL19_Falanga.pdf
Our research pages:
Vision-based quadrotor navigation: http://rpg.ifi.uzh.ch/research_mav.html
Aggressive quadrotor flight: http://rpg.ifi.uzh.ch/aggressive_flight.html
Event-based vision: http://rpg.ifi.uzh.ch/research_dvs.html
Affiliations: D. Falanga, S. Kim and D. Scaramuzza are with the Robotics and Perception Group, Dept. of Informatics, University of Zurich, and Dept. of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland http://rpg.ifi.uzh.ch/
Видео Rapid, Dynamic Obstacle Avoidance with an Event-based Camera канала UZH Robotics and Perception Group
Reference:
D. Falanga, S. Kim, D. Scaramuzza, "How Fast is Too Fast? The Role of Perception Latency in High-Speed Sense and Avoid", IEEE Robotics and Automation Letters (RA-L), 2019.
PDF: http://rpg.ifi.uzh.ch/docs/RAL19_Falanga.pdf
Our research pages:
Vision-based quadrotor navigation: http://rpg.ifi.uzh.ch/research_mav.html
Aggressive quadrotor flight: http://rpg.ifi.uzh.ch/aggressive_flight.html
Event-based vision: http://rpg.ifi.uzh.ch/research_dvs.html
Affiliations: D. Falanga, S. Kim and D. Scaramuzza are with the Robotics and Perception Group, Dept. of Informatics, University of Zurich, and Dept. of Neuroinformatics, University of Zurich and ETH Zurich, Switzerland http://rpg.ifi.uzh.ch/
Видео Rapid, Dynamic Obstacle Avoidance with an Event-based Camera канала UZH Robotics and Perception Group
Показать
Комментарии отсутствуют
Информация о видео
7 мая 2019 г. 19:47:43
00:02:35
Другие видео канала
![Quadcopter mapping, path planning and controls for Obstacle avoidance.](https://i.ytimg.com/vi/ZjnwAPUFEPk/default.jpg)
![Easy Programming of Tello Drone | Python OpenCV Object Tracking](https://i.ytimg.com/vi/vDOkUHNdmKs/default.jpg)
![The astounding athletic power of quadcopters | Raffaello D'Andrea](https://i.ytimg.com/vi/w2itwFJCgFQ/default.jpg)
![Insightness Collision Avoidance for Drones](https://i.ytimg.com/vi/pAI_ZJOD7zQ/default.jpg)
![Pushbroom Stereo for High-Speed Obstacle Avoidance (technical video)](https://i.ytimg.com/vi/iksfHQkkq88/default.jpg)
![Davide Scaramuzza and Guillermo Gallego. Event-based Cameras: Challenges and Opportunities](https://i.ytimg.com/vi/SU_Fp4xS_g4/default.jpg)
![Robust, Visual-Inertial State Estimation: from Frame-based to Event-based Cameras](https://i.ytimg.com/vi/5-fqEGgt-b8/default.jpg)
![How To Make A DIY Arduino Obstacle Avoiding Car At Home](https://i.ytimg.com/vi/1n_KjpMfVT0/default.jpg)
![What is Event-Based Vision | Metavision by Prophesee](https://i.ytimg.com/vi/MjX3z-6n3iA/default.jpg)
![Event Cameras: Opportunities and the Road Ahead (CVPR 2020)](https://i.ytimg.com/vi/6Sn9-M7qXLk/default.jpg)
![#227 The ugly truth about LIDARs for obstacle avoidance (RPLIDAR A1, Arduino, ESP8266)](https://i.ytimg.com/vi/AERfie9wlWM/default.jpg)
![Why Use 3D-Printed Drones? | National Geographic](https://i.ytimg.com/vi/92wlASzGKbI/default.jpg)
![Drone Simulation and Control, Part 1: Setting Up the Control Problem](https://i.ytimg.com/vi/hGcGPUqB67Q/default.jpg)
![Meet the dazzling flying machines of the future | Raffaello D'Andrea](https://i.ytimg.com/vi/RCXGpEmFbOw/default.jpg)
![Obstacle Avoidance(part1) | DIY | On Any Drone | DIYLIFEHACKER](https://i.ytimg.com/vi/KI76nA7P5MI/default.jpg)
![Is LIDAR easy to use for hobbyists? DIY Roomba? Obstacle Avoidance System for Robotics](https://i.ytimg.com/vi/_--8K1BW_O4/default.jpg)
![Control of Mobile Robots- 2.8 Obstacle Avoidance](https://i.ytimg.com/vi/bsdBFHMSI2E/default.jpg)
![Robots that fly ... and cooperate | Vijay Kumar](https://i.ytimg.com/vi/4ErEBkj_3PY/default.jpg)
![Dynamic Obstacle Avoidance for Quadrotors with Event Cameras (Science Robotics 2020)](https://i.ytimg.com/vi/BzykucxFddI/default.jpg)
![How to Make Arduino Obstacle Avoiding Robot with L298N H-Bridge Motor Driver](https://i.ytimg.com/vi/tXsP9STxdBc/default.jpg)