Collision avoidance based on predictive probability using Kalman filter
2
조회
0
다운로드
8
인용
0
참고문헌
키워드
초록
In this paper, a collision avoidance algorithm based on predictive probability using the Kalman filter is proposed. Existing algorithms are based on the Time to the Closest Point of Approach (TCPA) and Distance to the Closest Point of Approach (DCPA) derived from geometric data between own ship and target ships using current states (heading angle and velocity). When compared to these approaches, the proposed algorithm is capable of predicting the states and easy to plan optimal path by considering the uncertainty in avoidance situation based on the number of ships. In this study, an Unscented Kalman Filter (UKF) is used due to the nonlinearities in the state variables to be predicted. By using the predicted state variables of the ships calculated via the UKF's prediction step, the positions of the number of ships after a certain time are derived as a predictive probability. Then, the validation of the proposed algorithm is examined by planning the optimal path in the collision avoidance simulations by applying the predictive probability.
Abstract
In this paper, a collision avoidance algorithm based on predictive probability using the Kalman filter is proposed. Existing algorithms are based on the Time to the Closest Point of Approach (TCPA) and Distance to the Closest Point of Approach (DCPA) derived from geometric data between own ship and target ships using current states (heading angle and velocity). When compared to these approaches, the proposed algorithm is capable of predicting the states and easy to plan optimal path by considering the uncertainty in avoidance situation based on the number of ships. In this study, an Unscented Kalman Filter (UKF) is used due to the nonlinearities in the state variables to be predicted. By using the predicted state variables of the ships calculated via the UKF's prediction step, the positions of the number of ships after a certain time are derived as a predictive probability. Then, the validation of the proposed algorithm is examined by planning the optimal path in the collision avoidance simulations by applying the predictive probability.
참고문헌 (19)
- Armin, S., "Predictive Probability Based Collision Avoidance for Unmanned Aerial Vehicles", ~ (2019)
- Chen, D., "A research on AIS-based embedded system for ship collision avoidance", 2015 International Conference on Transportation Information and Safety (ICTIS), pp.512~517 (2015)
- 조용훈, "국제해상충돌예방규칙을 고려한 확률적 속도 장애물 기반의 선박 충돌회피 알고리즘", 대한조선학회 논문집, 56(1), pp.75~81 (2019), 대한조선학회[DOI]
- Fulgenzi, C., "Combining probabilistic velocity obstacles and occupancy grid for safe navigation in dynamic environments", Workshop on safe Navigation, IEEE ICRA (2007)
- Furukawa, Y., "Development of automatic course modification system using fuzzy inference", IFAC Proceed, 37, pp.77~82 (2004)[DOI]
- 한준희, "실내 이동로봇의 UKF 위치 추정 및 성능 평가", 한국지능시스템학회 논문지, 25(4), pp.361~368 (2015), 한국지능시스템학회
- Hu, Y., "Multi-ship collision avoidance decision-making based on collision risk index", J. Mar. Sci. Eng, 8, pp.640~ (2020)
- International Maritime Organization(IMO), "MSC 101", 5, pp.2019, ~
- 김동함, "심층 결정론적 정책 경사법을 이용한 선박 충돌 회피 경로 결정", 대한조선학회 논문집, 56(1), pp.58~65 (2019), 대한조선학회[DOI]
- Kuwata, Y., "Safe Maritime autonomous navigation with COLREGS, using velocity obstacles", IEEE J. Ocean. Eng, 39(1), pp.110~119 (2014)
- 이준하, "Unscented Kalman filter를 이용한 위치측정 센서융합", 한국지능시스템학회 논문지, 21(5), pp.667~672 (2011), 한국지능시스템학회
- 이윤석, "충돌위험 회피를 위한 선박 운항자의 초동조치에 관한 연구", 한국항해항만학회지, 38(4), pp.327~333 (2014), 한국항해항만학회[DOI]
- Namgung, H., "Inference rule of collision risk index based on ship nearcollision via adaptive neuro fuzzy inference system", Adv. Sci. Technol. Eng. Syst. J, 4(4), pp.152~160 (2019)
- Roth, M., "EKF", UKF maneuvering target tracking using coordinated turn models with polar, 17th International Conference on Information Fusion (FUSION), pp.2014[DOI]
- Son, K., "부유체운동 조종" (2014), Dasom Publishing
- 손남선, "시뮬레이터 기반 퍼지알고리즘과 환경스트레스모델을 이용한 선박 충돌위험도 추정에 관한 연구", 한국항해항만학회지, 33(1), pp.43~50 (2009), 한국항해항만학회
- Tam, C., "Collision risk assessment for ships", J. Mar. Sci. Technol, 15, pp.257~270 (2010)
- Thor, I., Fossen, "Guidance and Control of Ocean Vehicles" (1994), John Wiley & Sons
- Woo, J., "Collision Avoidance for an Unmanned Surface Vehicle Using Deep Reinforcement Learning", Doctor, pp.2018