| 1 |
认知机器人学导言
学习目标，远程探索，基于模型的规划 |
Muscettola, N., P. Nayak, B. Pell, and B.
Williams. "Remote Agent: To Boldly Go Where No AI System Has Gone Before."
Artificial Intelligence 103 (1998): 5-47.
Bohlin, R., and
L. Kavraki. "Path Planning Using Lazy PRM." Intl Conf on Robotics
and Automation (ICRA) 1 (2000): 521-528.
Hsu, D., R. Kindel,
J. C. Latombe, and S. Rock. "Randomized Kinodynamic Motion Planning with
Moving Obstacles." Fourth International Workshop on Algorithmic
Foundations of Robotics, 2000. (PDF)
LaValle, Steven M. "Rapidly-Exploring Random Trees: A New Tool for Path
Planning." Technical Report No. 98-11, Dept. of Computer
Science, Iowa State University, October 1998. |
| 机器人灵敏导航 |
| 2 |
Kinodynamic随机路径规划
复习构型空间，可视图，Voronoi图，势场，和栅格分解法。
Kino-dynamic 规划，有运动障碍物的规划，随机路图 (PMs)，快速探索随机树（RRTs） |
|
| 3 |
同时定位和地图构建 (SLAM) 概述 (客座教师：Paul Robertson)
定位， SLAM，
卡尔曼滤波，大范围 SLAM |
Leonard, J., and P. Newman. "Consistent,
Convergent, and Constant-Time SLAM." In 18th International Joint
Conference on Artificial Intelligence. Acapulco, Mexico, August 2003.
(PDF)
Eliazar, Austin, and Ronald Parr. "DP-SLAM:
Fast, Robust Simultaneous Localization and Mapping Without Predetermined
Landmarks." In 18th International Joint Conference on Artificial
Intelligence. Acapulco, Mexico, August 2003. (PDF) |
| 4 |
基于视觉的SLAM (客座教师: Paul Robertson)
拓扑地图，隐马尔可夫模型 (HMM)， SIFT，基于视觉的定位 |
|
| 状态推演和故障诊断 |
| 5 |
基于模型的诊断和模式估计
基于一致性的诊断：候选， 冲突，诊断，和内核诊断
冲突抽象和候选生成，模式估计和概率诊断，主动探测。 |
De Kleer, Johan, Alan K. Mackworth, and Raymond
Reiter. "Characterizing Diagnoses and Systems." Artificial
Intelligence 56 (1992). |
| 6 |
通过冲突学习解决最优约束满足问题
最优约束满足问题，基于约束的A*，冲突指导 A*，冲突提取 |
Williams, Brian C., and Robert Ragno.
"Conflict-directed A* and its Role in Model-based Embedded Systems."
Journal of Discrete Applied Math (January 2003). (Appears in the
Special Issue on Theory and Applications of Satisfiability Testing.) |
| 关于软约束的推理 |
| 7 |
软约束满足问题 (SCSPs)
(客座教师: Martin Sachenbacher)
值约束满足问题 (VCSPs)，软约束的分枝限界法搜索，软约束的变量消除，树分解，动态规划 |
Schiex, J. T., H. Fargier, and G. Verfaillie. "Valued Constraint Satisfaction Problems: Hard and easy
problems." In Proceedings of the International Joint Conference in
AI (IJCAI-95). Montreal, Canada, 1995.
Dechter, Rina. "Tree
Decomposition Methods," and "Constraint Optimization." Chapter 9 and 13 in
Constraint Processing. San Francisco, CA:
Morgan Kaufmann Publishers, 2003. ISBN: 1558608907. |
| 8 |
用分解法和抽象法解决 CSPs 和 SCSPS (客座教师： Martin Sachenbacher)
化简有序二分决策图
(ROBDDs)， 用代数决策图 (ADDs) 表述和运用软约束 |
Bryant, Randal E. "Graph-Based Algorithms for Boolean Function
Manipulation." IEEE Transactions on Computers C-35, no. 8 (1986):
677-691. (PDF)
Bahar, R. I., E. A. Frohm, C. M. Gaona, G.
D. Hachtel, E. Macii, A. Pardo, and F. Somenzi. "Algebraic decision diagrams and their applications." In
Proceedings of the International Conference on Computer-Aided
Design. 1993, pp. 188-191. |
| 复杂任务规划 |
| 9 |
任务级的任务规划 (客座教师：Robert
Tappan Morris)
偏序规划，基于约束的区间规划，和简单时间网络 (STNs) |
Smith, David E., Jeremy Frank, and Ari Jonsson.
"Bridging the Gap between Planning and Scheduling." Knowledge
Engineering Review 15, no. 1 (2000).
Kim, P., B. Williams, and
M. Abramson. "Executing Reactive, Model-based Programs through Graph-based
Temporal Planning." In International Joint Conference on Artificial
Intelligence. 2001, pp. 487-493.
Morris, Paul, Robert Morris,
Lina Khatib, Sailesh Ramakrishnan, and Andrew Bachmann. "Strategies for
Global Optimization of Temporal Preferences." Proceedings of the 10th
International Conference on Principles and Practice of Constraint
Programming, CP 2004, Toronto, Canada. |
| 10 |
不确定性条件下的动态规划与执行，
STNS，
可调度网络和调度执行，STNUs， 强动态可控性 |
Dechter, R., I. Meiri, and J. Pearl. "Temporal Constraint Networks"
Artificial Intelligence (1991).
Muscettola, N., and P.
Morris. "Execution of Temporal Plans with Uncertainty." (PDF) |
| 11 |
人与机器人的混合探索 (客座教师: Jeff
Hoffman) |
|
| 机器人的运行中规划 |
| 12 |
隐状态和基于模型的反应式规划
通用规划，针对结构分解的基于模型的反应式规划 (MRP)， 二分决策图， 表征
MRP |
Ingham, Ragno, and Williams. "A Reactive Planner
for a Model-based Executive." In Proceedings of the 15th International
Joint Conference on Artificial Intelligence (IJCAI-97). |
| 13 |
连续，增量式路径规划和探索
单源最短路径， D*， LRTA* |
Koenig, S., and M. Likhachev. "Incremental A*." In
Advances in Neural Information Processing Systems
14. Cambridge, MA: MIT Press, 2002. ISBN: 0262042088. (NIPS)
Stentz,
A. "Optimal and Efficient Path Planning for Partially-Known Environments."
In Proceedings of IEEE International Conference on Robotics and
Automation, May 1994. (PDF) |
| 14 |
POMDPs规划 (学生报告人：
Brian Bairstow, Tony Jimenez, and Larry Bush)
POMDPs基础简介,POMDP 技术研究现状,不同算法的一个教学说明 |
Theocharous, Georgios, and Leslie Pack Kaelbling.
"Approximate Planning in POMDPS with Macro-Actions." In Advances in Neural Information Processing Systems
16. Cambridge, MA: MIT Press, 2004. ISBN: 0262201526. Vancouver,
(NIPS-03).
Roy, N., G. Gordon and S. Thrun. "Finding Approximate
POMDP solutions Through Belief Compression." Journal of Artificial
Intelligence Research 23 (2005): 1-40.
Roy, N. "PhD Thesis:
Finding Approximate POMDP Solutions Through Belief Compression." Robotics
Institute, Carnegie Mellon University, 2003.
Russell, Stuart, and
Peter Norvig. Artificial Intelligence: A Modern Approach. 2nd
ed. New York, NY: Prentice Hall, 2002. ISBN: 0137903952. [also available
for purchase on Amazon.com ]
Kaelbling, Leslie Pack, Michael L.
Littman, and Anthony R. Cassandra. "Planning and Acting in Partially
Observable Stochastic Domains." Artificial Intelligence 101
(1998).
Hiller, F., and G. Lieberman. Introduction to Operations Research. 7th ed.
New York, NY: McGraw Hill, 2002. ISBN: 0072535105.
Jaakkola,
T., S. Singh, and M. Jordan. "Reinforcement Learning Algorithm for
Partially Observable Markov Decision Problems." Advances In Neural Information Processing
Systems. Cambridge, MA: MIT Press, 1995. ISBN: 0262201046. (PDF)
Theocharous, Georgios, Kevin Murphy, and
Leslie Pack Kaelbling. "Representing hierarchical POMDPs as DBNs for
multi-scale robot localization." In International Conference on
Robotics and Automation, 2004. |
| 15 |
德克萨斯州 Hold'em Poker项目中，基于模型的多智能体推理 (学生报告人： Brian Edward Mihok and Michael Terry)
博弈推理的主流技术，不确定技术的重点介绍
隐马尔可夫模型和贝叶斯推理，神经网络 |
Rabiner, L. R. "A tutorial on Hidden Markov Models and selected
applications in speech recognition." Proceedings of the IEEE 77,
no. 2 (1989): 257-286. (PDF)
Friedman, N., I. Nachman, and D. Pe'er.
"Learning bayes network structure from massive datasets: The "sparse
candidate" algorithm." Uncertainty in Artificial Intelligence 15
(1999): 206-215.
Ennis, M., G. Hinton, D. Naylor, M. Revow, and R.
Tibshirani. "A comparison of statistical learning methods on the GUSTO
database." Stat Med 17, no. 21 (1998): 2501-2508.
Moore,
Andrew. "Tutorial on Bayes Nets." (Microsoft® PowerPoint® lecture.) (PDF)
Dietterich, T. G. "Machine Learning for
Sequential Data: A Review." In Structural, Syntactic, and Statistical Pattern
Recognition; Lecture Notes in Computer Science. Vol. 2396. Edited
by T. Caelli. New York, NY: Springer, 2002, pp. 15-30. ISBN: 3540440119.
(PDF)
Bilmes, Jeff. "What HMMs Can Do." UWEE
Technical Report Number UWEETR-2002-0003. January 2002. |
| 16 |
认知博弈论 (学生报告人：
Justin Fox, Jeremie Pouly, and Jennifer Novosad)
基本原理及其扩展
一个应用于国际象棋的进化算法
归纳式的对手模拟 |
Gross, R., K. Albrecht, W. Kantschik, and W.
Banzhaf. "Evolving Chess Playing Programs." Proceedings of the Genetic
and Evolutionary Computation Conference, 2002.
Walczak,
Steven. "Knowledge-Based Search in Competitive Domains." IEEE
Transactions on Knowledge and Data Engineering 15, no. 3 (May/June
2003).
Banzhaf, W., P. Nordin, R. E. Keller, and F. D. Francone. Genetic Programming - An Introduction On The Automatic
Evolution of Computer Programs and its Applications. San
Francisco, CA: Morgan Kaufman, 1997. ISBN: 155860510X.
Schaeffer,
J. "The History Heuristic and Alpha-Beta Search Enhancements in Practice."
IEEE Transactions on Pattern Analysis and Machine Intelligence
11, no. 11 (1989): 1203-1212.
Schwefel, H. P. Evolution and Optimum Seeking. New York, NY:
John Wiley and Sons, Inc., 1996. ISBN: 0471571482.
Walczak, Steven.
"Improving Opening Book Performance Through Modeling of Chess
Opponents." ACM Annual Computer Science Conference,
1996. |
| 17 |
混合离散/连续系统的模式估计 (学生报告人： Lars Blackmore)
基于约束的HMMs的轨迹跟踪，混合HMMs高斯滤波
(K-Best 和 Rao-Blackwell粒子滤波) |
|
| 18 |
粒子滤波及其应用 (学生报告人：
Kaijen Hsiao, Jason Miller, and Henry Lefebvre de
Plinval-Salgues)
粒子滤波在SLAM中的故障诊断应用 |
Verma, Vandi, Geoff Gordon, Reid Simmons, and Sebastian Thrun.
"Particle Filters for Rover Fault Diagnosis." IEEE Robotics and
Automation Magazine special issue on Human Centered Robotics and
Dependability. June 2004. (PDF)
Thrun, Sebastian. "A Probabilistic Online
Mapping Algorithm for Teams of Mobile Robots." International Journal
of Robotics Research 20 (2001). (PDF)
Montemerlo, Michael, Sebastian Thrun, Daphne
Koller, and Ben Wegbreit. "FastSLAM: A Factored Solution to the
Simultaneous Localization and Mapping Problem." Proceedings of the
AAAI National Conference on Artificial Intelligence,
2002.
Stachniss, Cyrill, Giorgio Grisetti, and Wolfram Burgard.
"Recovering Particle Diversity in a Rao-Blackwellized Particle Filter for
SLAM After Actively Closing Loops." Proceedings of the IEEE
International Conference on Robotics and Automation, 2005. (PDF)
Thrun, Sebastian, John Langford, and Vandi
Verma. "Risk Sensitive Particle Filters." Proceedings of
Neural Information Processing Systems (NIPS), December,
2001.
Dearden, Richard, Frank Hutter, Reid Simmons, Sebastian
Thrun, Vandi Verma, and Thomas Willeke. "Real-time Fault Detection and
Situational Awareness for Rovers: Report on the Mars Technology Program
Task." To appear in the Proceedings of IEEE Aerospace Conference,
March 2004. (PDF) |
| 19 |
你好计算机？(学生报告人： Shuonan
Dong, Shen Qu, and Thomas Coffee)
共享规划，规划识别，和COLLAGEN |
Blaylock, Nate, and James Allen. "Statistical goal parameter recognition." 14th
International Conference on Automated Planning and Scheduling
(ICAPS'04). British Columbia, Whistler. June 3-7, 2004.
———.
"Corpus-based, statistical goal recognition."
Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence (IJCAI-2003). Acapulco, Mexico, August 9-15,
2003, pp. 1303-1308.
Rich, C., C. L. Sidner. "COLLAGEN: A
Collaboration Manager for Software Interface Agents." An International
Journal: User Modeling and User-Adapted Interaction 8, no. 3/4
(1998): 315-350. (PDF)
Lesh, N., C. Rich, Charles, and C. Sidner.
"Using Plan Recognition in Human-Computer Collaboration." In
Proceedings of the Seventh Int Conf on User Modelling. Banff,
Canada, July 1999. (PDF)
Grosz, Barbara, and Sarit Kraus. "The
Evolution of SharedPlans." In Foundations and Theories of Rational Agencies.
Edited by A. Rao and M. Wooldridge. New York, NY: Springer, 1999, pp.
227-262. ISBN: 0792356012. (PDF) |
| 20 |
贝叶斯网络的高级课题 (学生报告人： Tom Temple, Ethan Howe, and James
Lenfestey)
动态贝叶斯网络，精确推理，近似推理 (PF)，学习，概率关系模型，参数/结构估计 |
Ghahramani, Z. "Learning Dynamic Bayesian
Networks." In Adaptive Processing of Sequences and Data
Structures. Edited by C. L. Giles and M. Gori. Lecture Notes in
Artificial Intelligence. Berlin, Germany: Springer-Verlag, pp. 168-197.
ISBN: 3540643419.
Friedman, Nir, Lise Getoor, Daphne Koller, Avi
Pfeffer. Learning Probabilistic Relational Models. 14th
International Joint Conference on Artificial Intelligence. Montreal,
Canada, August 1995.
Russell, Stuart, and Peter Norvig. "Intro to
Bayesian networks. Probabilistic inference. PRM primer." and "Temporal
Bayesian models. HMMs and DBNs." Chapter 14 and 15 in Artifical Intelligence, A Modern Approach. New
York, NY: Prentice Hall, 2002. ISBN: 0137903952.
Myers, James,
Kathryn Laskey, and Tod Levitt. "Learning Bayesian Networks from
Incomplete Data with Stochastic Search Algorithms." Fifteenth
Conference on Uncertainty in Artificial Intelligence, 1999. (PDF)
Sanghai, Sumit, Pedro Domingos, and Daniel
Weld. "Dynamic Probabilistic Relational Models." 18th International
Joint Conference on Artificial Intelligence. Acapulco, Mexico, August
2003. (PDF)
Zweig, G., and S. Russell. "Speech Recognition with Dynamic Bayesian Networks." In
Proceedings of the AAAI-98. Madison, Wisconsin:
AAAI Press, 1998. ISBN: 0262510987. |
| 认知层次的感知和操纵 |
| 21 |
使用概率语法的可视化表述 (客座教师： Paul Robertson)
统计分析，图像分割，蒙特卡罗方法，语言学习 |
|
| 22 |
双足行走任务的安全执行 (客座教师： Andreas Hoffman)
目标和要求，双足平衡控制策略，普通控制方法（及其缺点），用基于模型执行的任务级别的控制，全身控制 |
Hofmann, A. G., M. B. Popovic, and H. M. Herr. "A
Sliding Controller for Bipedal Balancing Using Integrated Movement of
Contact and Non-Contact Limbs." Proceedings of IEEE/RSJ International
Conference on Intelligent Robots and Systems (IROS04). Sendai,
Japan.
———. "Angular Momentum Regulation During Human Walking."
International Conference on Robotics and Automation, 2004. |
| 人机交互 |
| 23 |
以人为搭档的工作和学习 (客座教师： Cynthia Breazeal)
多模型通讯，人机协同作业，社会引导学习 |
Lockerd, A., and C. Breazeal. "Tutelage and
Socially Guided Robot Learning." Proceedings of IEEE/RSJ International
Conference on Intelligent Robots and Systems (IROS04). Sendai, Japan,
2004.
Breazeal, C., A. Brooks, D. Chilongo, J. Gray, G. Hoffman, C.
Kidd, H. Lee, J. Lieberman, and A. Lockerd. "Working Collaboratively with
Humanoid Robots." Proceedings of Humanoids, Los Angeles, CA,
2004. |
| 24 |
医护机器人：对话的决策过程 (客座教师：Nick Roy)
基于模型的对话管理，不确定情况下的分层规划，人类交流的加强学习 |
Pineau, J., M. Montemerlo, M. Pollack, N. Roy, and
S. Thrun. "Towards robotic assistants in nursing homes: challenges and
results." Robotics and Autonomous Systems 42, no. 3-4 (March 31,
2003): 271-281.
Singh, Satinder, Diane Litman, Michael Kearns, and
Marilyn Walker. "Optimizing Dialogue Management with Reinforcement
Learning: Experiments with the NJFun System." Journal of Artificial
Intelligence Research (JAIR) 16 (2002): 105-133. (PDF) |
| 25 |
项目展示 |
|
| 26 |
项目展示 (续) |
|