소형 무인기(UAV: Unmanned Aerial Vehicle)가 급속히 대중화됨에 따라 최근의 UAV 시스템은 각각의 목적에 따라 다양한 분야에서 설계되고 활용되고 있다. 이는 UAV 조정과 관련하여 전자, 센서, 카메라, 소프트웨어 프로그램 등에 이르기까지 많은 새로운 기회를 열어 가고 있으며 저비용 및 혁신적 업무 수행 능력으로 UAV의 활용과 응용 영역의 확대는 새로운 기술 혁신을 주도하고 있다. 특히 소형 UAV는 저고도 상황에서 예측이 힘든 돌발 변화나 장애물 출현 발생 확률이 높은 환경에서 비행을 하여야 한다. 본 논문에서는 소형 UAV 시스템의 자율 비행 기술에 관한 최근의 연구를 소개하고 적대적인 환경에서 소형 UAV의 저비용 센서들을 활용하여 경로 생성과 충돌 회피를 통해 안전하게 목표물에 도착을 유도하는 시험적 방안을 제안 한다.
소형 무인기(UAV: Unmanned Aerial Vehicle)가 급속히 대중화됨에 따라 최근의 UAV 시스템은 각각의 목적에 따라 다양한 분야에서 설계되고 활용되고 있다. 이는 UAV 조정과 관련하여 전자, 센서, 카메라, 소프트웨어 프로그램 등에 이르기까지 많은 새로운 기회를 열어 가고 있으며 저비용 및 혁신적 업무 수행 능력으로 UAV의 활용과 응용 영역의 확대는 새로운 기술 혁신을 주도하고 있다. 특히 소형 UAV는 저고도 상황에서 예측이 힘든 돌발 변화나 장애물 출현 발생 확률이 높은 환경에서 비행을 하여야 한다. 본 논문에서는 소형 UAV 시스템의 자율 비행 기술에 관한 최근의 연구를 소개하고 적대적인 환경에서 소형 UAV의 저비용 센서들을 활용하여 경로 생성과 충돌 회피를 통해 안전하게 목표물에 도착을 유도하는 시험적 방안을 제안 한다.
With the fast growing popularity of small UAVs (Unmanned Aerial Vehicles), recent UAV systems have been designed and utilized for the various field with their own specific purposes. UAVs are opening up many new opportunities in the fields of electronics, sensors, camera, and software for pilots. Inc...
With the fast growing popularity of small UAVs (Unmanned Aerial Vehicles), recent UAV systems have been designed and utilized for the various field with their own specific purposes. UAVs are opening up many new opportunities in the fields of electronics, sensors, camera, and software for pilots. Increase in awareness and mission capabilities of UAVs are driving innovations and new applications driven with the help of low cost and its capability in undertaking high threat task. In particular, small unmanned aerial vehicles should fly in environments with high probability of unexpected sudden change or obstacle appearance in low altitude situations. In this paper, current researches regarding techniques of autonomous flight of smal UAV systems are introduced and we propose a draft idea for planning paths for small unmanned aerial vehicles in adversarial environments to arrive at the given target safely with low cost sensors.
With the fast growing popularity of small UAVs (Unmanned Aerial Vehicles), recent UAV systems have been designed and utilized for the various field with their own specific purposes. UAVs are opening up many new opportunities in the fields of electronics, sensors, camera, and software for pilots. Increase in awareness and mission capabilities of UAVs are driving innovations and new applications driven with the help of low cost and its capability in undertaking high threat task. In particular, small unmanned aerial vehicles should fly in environments with high probability of unexpected sudden change or obstacle appearance in low altitude situations. In this paper, current researches regarding techniques of autonomous flight of smal UAV systems are introduced and we propose a draft idea for planning paths for small unmanned aerial vehicles in adversarial environments to arrive at the given target safely with low cost sensors.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
This paper proposes a path planning method for an autonomous flight in the indoor environment where GPS communication is impossible. Q-learning algorithm, a reinforcement learning algorithm, could be used.
제안 방법
This paper provided a brief introduction on current researches of small UAVs and proposed a draft idea for planning paths for small unmanned aerial vehicles in adversarial environments to arrive at the given target safely with low cost sensors. For this purpose, this paper creates a map that assumes an indoor environment and suggests a path planning method through reinforcement learning and UAV positioning technique using lazy recalibration. Future work will include real implementations and simulation results.
This paper introduces current researches regarding techniques of autonomous flight of small UAV systems and proposes a draft idea for planning paths for small unmanned aerial vehicles in adversarial environments to arrive at the given target safely with low cost sensors.
This paper provided a brief introduction on current researches of small UAVs and proposed a draft idea for planning paths for small unmanned aerial vehicles in adversarial environments to arrive at the given target safely with low cost sensors. For this purpose, this paper creates a map that assumes an indoor environment and suggests a path planning method through reinforcement learning and UAV positioning technique using lazy recalibration.
이론/모형
This paper proposes a path planning method for an autonomous flight in the indoor environment where GPS communication is impossible. Q-learning algorithm, a reinforcement learning algorithm, could be used. Thus UAVs may determine their own path based on the learned results.
The authors identified a vision-based system with a low-cost camera device. The information carried by the camera is integrated with the classical data from the IMU and GPS in the sensor fusion algorithm. Lingyun Xu et al.
Chen, H., Chang, K., & Agate, C. S., UAV path planning with tangent-plus-Lyapunov vector field guidance and obstacle avoidance. IEEE Transactions on Aerospace and Electronic Systems, 49(2), 2013, 840-856.
Chicarella, S., Ferrara, V., Frezza, F., D'Alvano, A., & Pajewski, L. (2016, December). Improvement of GPR tracking by using inertial and GPS combined data. In Software, Telecommunications and Computer Networks, 2016 24th Int'l Conference on, pp. 1-5.
Bhatia, S., Yang, H., Zhang, R., & Reindl, L. (2016, March). Development of an analytical method for IMU calibration. In 2016 13th Int'l Multi-Conference on Systems, Signals & Devices (SSD), 131-135.
Angelino, C. V., Baraniello, V. R., & Cicala, L. (2012, July). UAV position and attitude estimation using IMU, GNSS and camera. In Information Fusion, 2012 15th Int'l Conference on, 735-742.
Xu, L., & Luo, H. (2016, June). Towards autonomous tracking and landing on moving target. In Real-time Computing and Robotics (RCAR), IEEE Int'l Conference on, 620-628
YAU, Kok-Lim Alvin; KOMISARCZUK, Peter; TEAL, Paul D. A context-aware and intelligent dynamic channel selection scheme for cognitive radio networks. In: Cognitive Radio Oriented Wireless Networks and Communications, 2009. CROWNCOM'09. 4th International Conference on. IEEE, 2009. p. 1-6.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.