2차원 라이다 센서 데이터 분류를 이용한 적응형 장애물 회피 알고리즘
Adaptive Obstacle Avoidance Algorithm using Classification of 2D LiDAR Data
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper presents an adaptive method to avoid obstacles in various environmental settings, using a two-dimensional (2D) LiDAR sensor for mobile robots. While the conventional reaction based smooth nearness diagram (SND) algorithms use a fixed safety distance criterion, the proposed algorithm autonomously changes the safety criterion considering the obstacle density around a robot. The fixed safety criterion for the whole SND obstacle avoidance process can induce inefficient motion controls in terms of the travel distance and action smoothness. We applied a multinomial logistic regression algorithm, softmax regression, to classify 2D LiDAR point clouds into seven obstacle structure classes. The trained model was used to recognize a current obstacle density situation using newly obtained 2D LiDAR data. Through the classification, the robot adaptively modifies the safety distance criterion according to the change in its environment. We experimentally verified that the motion controls generated by the proposed adaptive algorithm were smoother and more efficient compared to those of the conventional SND algorithms.
Abstract
This paper presents an adaptive method to avoid obstacles in various environmental settings, using a two-dimensional (2D) LiDAR sensor for mobile robots. While the conventional reaction based smooth nearness diagram (SND) algorithms use a fixed safety distance criterion, the proposed algorithm autonomously changes the safety criterion considering the obstacle density around a robot. The fixed safety criterion for the whole SND obstacle avoidance process can induce inefficient motion controls in terms of the travel distance and action smoothness. We applied a multinomial logistic regression algorithm, softmax regression, to classify 2D LiDAR point clouds into seven obstacle structure classes. The trained model was used to recognize a current obstacle density situation using newly obtained 2D LiDAR data. Through the classification, the robot adaptively modifies the safety distance criterion according to the change in its environment. We experimentally verified that the motion controls generated by the proposed adaptive algorithm were smoother and more efficient compared to those of the conventional SND algorithms.
참고문헌 (17)
- 이승환, "실외 자율 로봇 주행을 위한 센서 퓨전 시스템 구현", 센서학회지, 19(3), pp.246~257 (2010), 한국센서학회
- 손민혁, "시각을 이용한 이동 로봇의 강건한 경로선 추종 주행", 센서학회지, 20(3), pp.178~186 (2011), 한국센서학회
- 권오상, "이동로봇의 자동충전을 위한 어안렌즈 카메라의 보정 및 인공표지의 검출", 센서학회지, 14(4), pp.278~285 (2005), 한국센서학회
- J. Minguez, "Nearness diagram(ND)navigation : Collision avoidance in troublesome scenarios", IEEE Trans. Rob. Autom, 20(1), pp.45~59 (2004)
- M. Mujahed, "Smooth and safe Nearness-Diagram(SSND)Navigation for autonomous mobile robots", Adv. Mater. Res., 403-408, pp.4718~4726 (2012)
- M. Mujahed, "Tangential closest gap based(TCG)reactive obstacle avoidance navigation for cluttered environments", IEEE Int. Symp. On Saf. Secur. Rescue Rob., pp.1~6 (2013)
- M. Mujahed, "Admissible gap navigation : A new collision avoidance approach", Rob. Auton. Syst, 103, pp.93~110 (2018)
- M. Mujahed, "Safe gap based(SG)reactive navigation for mobile robots", Eur. Conf. Mob. Robot, pp.325~330 (2013)
- M. Mujahed, "Tangential Gap Flow(TGF)navigation : A new reactive obstacle avoidance approach for highly cluttered environments", Rob. Auton. Syst, 84, pp.15~30 (2016)
- F. Bonin-Font, "Vision-based mobile robot motion control combining T2 and ND approaches", Robotica, 32(4), pp.591~609 (2014)
- J. Minguez, "A “divide and conquer”strategy based on situations to achieve reactive collision avoidance in troublesome scenarios", IEEE Int. Conf. on Robot. Autom, pp.3855~3862 (2004)
- J. W. Durham, "Smooth Nearness-Diagram Navigation", Int. Conf. on Intell. Robot. Syst, pp.690~695 (2008)
- D. R. Cox, "The Regression Analysis of Binary Sequences", J. R. Stati. Soc. Series B Stat. Methodol, 20(2), pp.238~238 (1958)
- J. Engel, "Polytomous logistic regression", Stat. Neerl, 42(4), pp.233~252 (1988)
- S. H. Walker, "Estimation of the probability of an event as a function of several independent variables", Biometrika, 54(1-2), pp.167~179 (1967)
- J. W. Gibbs, "Elementary Principles in Statistical Mechanics", pp.32~45 (1902), Yale University Press
- M. Mujahad, "Closest Gap based(CG)reactive obstacle avoidance navigation for highly cluttered environments", Proc. IEEE, 2010, 1805~1812