도시환경 매핑 시 SLAM 불확실성 최소화를 위한 강화 학습 기반 경로 계획법
RL-based Path Planning for SLAM Uncertainty Minimization in Urban Mapping
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
For the Simultaneous Localization and Mapping (SLAM) problem, a different path results in different SLAM results. Usually, SLAM follows a trail of input data. Active SLAM, which determines where to sense for the next step, can suggest a better path for a better SLAM result during the data acquisition step. In this paper, we will use reinforcement learning to find where to perceive. By assigning entire target area coverage to a goal and uncertainty as a negative reward, the reinforcement learning network finds an optimal path to minimize trajectory uncertainty and maximize map coverage. However, most active SLAM researches are performed in indoor or aerial environments where robots can move in every direction. In the urban environment, vehicles only can move following road structure and traffic rules. Graph structure can efficiently express road environment, considering crossroads and streets as nodes and edges, respectively. In this paper, we propose a novel method to find optimal SLAM path using graph structure and reinforcement learning technique.
Abstract
For the Simultaneous Localization and Mapping (SLAM) problem, a different path results in different SLAM results. Usually, SLAM follows a trail of input data. Active SLAM, which determines where to sense for the next step, can suggest a better path for a better SLAM result during the data acquisition step. In this paper, we will use reinforcement learning to find where to perceive. By assigning entire target area coverage to a goal and uncertainty as a negative reward, the reinforcement learning network finds an optimal path to minimize trajectory uncertainty and maximize map coverage. However, most active SLAM researches are performed in indoor or aerial environments where robots can move in every direction. In the urban environment, vehicles only can move following road structure and traffic rules. Graph structure can efficiently express road environment, considering crossroads and streets as nodes and edges, respectively. In this paper, we propose a novel method to find optimal SLAM path using graph structure and reinforcement learning technique.
참고문헌 (12)
- C. Leung, "Active SLAM using Model Predictive Control and Attractor based Exploration", 2006IEEE, 2006, ~
- E. W. Dijkstra, "A note on two problems in connexion with graphs", Numerische Mathematik, 1(1), pp.269~271 (1959), Springer Science and Business Media LLC[DOI]
- Peter Hart, "A Formal Basis for the Heuristic Determination of Minimum Cost Paths", IEEE Transactions on Systems Science and Cybernetics, 4(2), pp.100~107 (1968), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- S. Singh, "Robust Reinforcement Learning in Motion Planning", Advances in Neural Information Processing Systems 6 (NIPS 1993) (1993)
- Andrew W. Moore, "The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces", Machine Learning, 21(3), pp.199~233 (1995), Springer Science and Business Media LLC[DOI]
- 박정준, "Path Planning for a Robot Manipulator based on Probabilistic Roadmap and Reinforcement Learning", International Journal of Control, Automation, and Systems, 5(6), pp.674~680 (2007), 제어·로봇·시스템학회
- Baochang Zhang, "Geometric Reinforcement Learning for Path Planning of UAVs", Journal of Intelligent & Robotic Systems, 77(2), pp.391~409 (2015), Springer Science and Business Media LLC[DOI]
- T. Kollar, "Trajectory Optimization using Reinforcement Learning f or M ap E xploration", The International Journal of Robotics Research, 27(2), pp.175~196 (2008)
- Liz Murphy, "Risky Planning on Probabilistic Costmaps for Path Planning in Outdoor Environments", IEEE Transactions on Robotics, 29(2), pp.445~457 (2013), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- L. Nardi, "Actively Improving Robot Navigation On Different Terrains Using Gaussian Process Mixture Models", 2019 International Conference on Robotics and Automation(ICRA) (2019)
- T. Shan, "LeGO-LOAM : Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain", 2018 IEEE, 2018, ~
- A. Dosovitskiy, "CARLA: An Open Urban Driving Simulator", 1st Annual Conference on Robot Learning, PMLR, 78, pp.1~16 (2017)