基于轨迹分析的自主导航性能评估方法

doi:10.3969/j.issn.1000-3428.2011.06.049

摘要/Abstract

摘要： 在马尔可夫决策模型框架下，提出一种基于轨迹分析的计算评估方法，通过分析驾驶回报设置和车辆轨迹的特征期望衡量自主导航系统的性能。假定回报函数是回报特征的线性组合，通过逼近不同的车辆自主驾驶策略，求解应用于沙盒场景的回报设置，从而仿真导航轨迹的特征期望。实验结果表明，该方法能对自主导航系统的轨迹数据实现定性和定量评估。

关键词: 轨迹分析, 自主导航性能评估, 马尔可夫决策过程

Abstract: This paper proposes a novel trajectory-analysis-based performance evaluation method, which assesses and compares the navigation performances by reward settings and feature expectations under Markov Decision Process(MDP) framework. Assuming that the reward function is a linear combination of known features, this method evaluates reward settings by approximating the driving styles of different land autonomous navigation systems. On this basis, reward settings are used to simulate the feature expectations of navigation trajectories in a standard land navigation environment called the sandbox. Experimental results show the validity of this method in both qualitative and quantitative performance evaluations.

Key words: trajectory analysis, autonomous navigation performance evaluation, Markov Decision Process(MDP)

中图分类号:

TP393

王勇鑫, 钱徽, 金卓军, 朱淼良. 基于轨迹分析的自主导航性能评估方法[J]. 计算机工程, 2011, 37(6): 141-144.

WANG Yong-Xin, JIAN Hui, JIN Zhuo-Jun, SHU Miao-Liang. Autonomous Navigation Performance Evaluation Method Based on Trajectory Analysis[J]. Computer Engineering, 2011, 37(6): 141-144.

http://www.ecice06.com/CN/Y2011/V37/I6/141

参考文献

[1] O’day S. Metrics for Intelligent Autonomy[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2004. [2] Zadeh L A. The Search for Metrics of Intelligence——A Critical View[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2000. [3] Bien Z, Kim Y T. How to Measure the Machine Intelligence Quotient(MIQ): Two Methods and Applications[C]//Proc. of the World Automation Congress. Anchorage, Alaska, USA: [s. n.], 1998. [4] Huang Huimin. Autonomy Levels for Unmanned Systems(ALF US) Framework: Safety and Application Issues[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2007. [5] Evans J M. Definitions and Measures of Intelligence in Deep Blue and the Army XUV[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2007. [6] Dufourd D, Dalgalarrondo A. Results and Lessons Learned from the Quantitative Evaluation of Road Detection and Tracking Algorithms[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2003. [7] Shirkhodaie A, Amrani R, Chawla N. Traversable Terrain Model- ing and Performance Measurement of Mobile Robots[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2004. [8] Nau D, Ghallab M. Measuring the Performance of Automated Planning Systems[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2004. [9] Shneier M, Shackleford W, Tsai H. Performance Evaluation of a Terrain Traversability Learning Algorithm in the DARPA LAGR Program[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2006. [10] Wagan A I, Godi A, Li Xiaolan. Map Quality Assessment[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2008. [11] Censi A. The Role of Bayesian Bounds in Comparing SLAM Algorithms Performance[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2008. [12] James C S. Reliability Estimation and Confidence Regions from Subsystem and Full System Tests via Maximum Likelihood[C]// Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2008. [13] Scrapper C, Balakirsky S, Weiss B. Autonomous Road Driving Arenas for Performance Evaluation[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2004. [14] Schlenoff C, Ajot J, Madhavan R. PRIDE: A Framework for Performance Evaluation of Intelligent Vehicles in Dynamic, On-road Environments[C]//Proc. of the Performance Metrics for Intelligent Systems Workshop. Gaithersburg, Maryland, USA: [s. n.], 2007. [15] Goyat Y, Chateau T, Malaterre L. Vehicle Trajectories Evaluation by Static Video Sensors[C]//Proc. of Intelligent Transportation Systems Conference. Toronto, Canada: [s. n.], 2006. [16] Sutton R S, Barto A G. Reinforcement Learning: An Introduc- tion[M]. Cambridge, USA: The MIT Press, 1993. [17] Ng A Y, Russell S. Algorithms for Inverse Reinforcement Learning[C]//Proc. of the 17th International Conference on Machine Learning. San Francisco, USA: [s. n.], 2000. [18] Abbeel P, Ng A Y. Apprenticeship Learning via Inverse Reinforcement Learning[C]//Proc. of the 21st International Conference on Machine Learning. Alberta, Canada: [s. n.], 2004. [19] Abbeel P, Coates A, Quigley M. An Application of Reinforcement Learning to Aerobatic Helicopter Flight[C]//Proc. of the 20th Annual Conference on Neural Information Processing Systems. Vancouver, Canada: [s. n.], 2007. [20] Abbeel P, Dolgov D, Ng A Y. Apprenticeship Learning for Motion Planning with Application to Parking Lot Navigation[C]//Proc. of the International Conference on Intelligent Robots and Systems. Nice, France: [s. n.], 2008. [21] Kolter J Z, Abbeel P, Ng A Y. Hierarchical Apprenticeship Learning with Applications to Quadruped Locomotion[C]//Proc. of the 21st Annual Conference on Neural Information Processing Systems. Vancouver, Canada: [s. n.], 2007. [22] Ratliff N D, J. Bagnell A. Maximum Margin Planning[C]//Proc. of the 23rd International Conference on Machine Learning. Pittsburgh, USA: [s. n.], 2006. [23] Syed U, Schapire R E. A Game-theoretic Approach to Apprenticeship Learning[C]//Proc. of NIPS’08. Vancouver, Canada: [s. n.], 2008. [24] Syed U, Bowling M, Schapire R E. Apprenticeship Learning Using Linear Programming[C]//Proc. of the 25th International Conference on Machine Learning. Helsinki, Finland: [s. n.], 2008. [25] Ramachandran D, Amir E. Bayesian Inverse Reinforcement Learning[C]//Proc. of the 20th International Joint Conference on Artificial Intelligence. Hyderabad, India: [s. n.], 2007. [26] Ziebart B D, Maas A, Bagnell J, et al. Maximum Entropy Inverse Reinforcement Learning[C]//Proc. of AAAI’08. Chicago, USA: [s. n.], 2008. [27] Neu G, Szepesvari C. Apprenticeship Learning Using Inverse Reinforcement Learning and Gradient Methods[C]//Proc. of the 23rd Conference Annual Conference on Uncertainty in Artificial Intelligence. Vancouver, Canada: [s. n.], 2007. [28] Ng A Y, Harada D, Russell S. Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping[C]// Proc. of the 16th International Conference on Machine Learning. Bled, Slovenia: [s. n.], 1999.

选择文件类型/文献管理软件名称

选择包含的内容