Cognitive Path Planning With Spatial Memory Distortion

被引:1
作者
Dubey, Rohit K. K. [1 ,3 ]
Sohn, Samuel S. S. [4 ]
Thrash, Tyler [5 ]
Hoelscher, Christoph [6 ]
Borrmann, Andre [2 ]
Kapadia, Mubbasir [4 ]
机构
[1] Tech Univ Munich, Chair Computat Modeling & Simulat, D-80333 Munich, Germany
[2] Tech Univ Munich, Dept Civil & Environm Engn, Munich, Germany
[3] Leonhard Obermeyer Ctr TUM, D-80333 Munich, Germany
[4] Rutgers State Univ, Comp Sci Dept, New Brunswick, NJ USA
[5] St Louis Univ, St Louis, MO 63103 USA
[6] Swiss Fed Inst Technol, CH-8092 Zurich, Switzerland
关键词
Cognitive path-planning; human wayfinding; fine-to-course; spatial memory; agglomerative hierarchical clustering; DISTANCE; DECAY; CATEGORIES; RETRIEVAL; MODEL; MAPS;
D O I
10.1109/TVCG.2022.3163794
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Human path-planning operates differently from deterministic AI-based path-planning algorithms due to the decay and distortion in a human's spatial memory and the lack of complete scene knowledge. Here, we present a cognitive model of path-planning that simulates human-like learning of unfamiliar environments, supports systematic degradation in spatial memory, and distorts spatial recall during path-planning. We propose a Dynamic Hierarchical Cognitive Graph (DHCG) representation to encode the environment structure by incorporating two critical spatial memory biases during exploration: categorical adjustment and sequence order effect. We then extend the "Fine-To-Coarse" (FTC), the most prevalent path-planning heuristic, to incorporate spatial uncertainty during recall through the DHCG. We conducted a lab-based Virtual Reality (VR) experiment to validate the proposed cognitive path-planning model and made three observations: (1) a statistically significant impact of sequence order effect on participants' route-choices, (2) approximately three hierarchical levels in the DHCG according to participants' recall data, and (3) similar trajectories and significantly similar wayfinding performances between participants and simulated cognitive agents on identical path-planning tasks. Furthermore, we performed two detailed simulation experiments with different FTC variants on a Manhattan-style grid. Experimental results demonstrate that the proposed cognitive path-planning model successfully produces human-like paths and can capture human wayfinding's complex and dynamic nature, which traditional AI-based path-planning algorithms cannot capture.
引用
收藏
页码:3535 / 3549
页数:15
相关论文
共 58 条
[1]   Decay Versus Interference: A New Look at an Old Interaction [J].
Altmann, Erik M. ;
Schunn, Christian D. .
PSYCHOLOGICAL SCIENCE, 2012, 23 (11) :1435-1437
[2]   Time causes forgetting from working memory [J].
Barrouillet, Pierre ;
De Paepe, Annick ;
Langerock, Naomi .
PSYCHONOMIC BULLETIN & REVIEW, 2012, 19 (01) :87-92
[3]   Factoring the Mapping Problem: Mobile Robot Map-building in the Hybrid Spatial Semantic Hierarchy [J].
Beeson, Patrick ;
Modayil, Joseph ;
Kuipers, Benjamin .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2010, 29 (04) :428-459
[4]  
Botea Adi, 2004, Journal of Game Development, V1, P1
[5]  
Briggs R., 1973, IMAGE ENV, P361
[6]   From Cognitive Maps to Cognitive Graphs [J].
Chrastil, Elizabeth R. ;
Warren, William H. .
PLOS ONE, 2014, 9 (11)
[7]   Sequence effects in estimating spatial location [J].
Crawford, L. Elizabeth ;
Duffy, Sean .
PSYCHONOMIC BULLETIN & REVIEW, 2010, 17 (05) :725-730
[8]  
Dubey R. K., 2019, P MOT INT GAM, p15:1
[9]   The cognitive map in humans: spatial navigation and beyond [J].
Epstein, Russell A. ;
Patai, Eva Zita ;
Julian, Joshua B. ;
Spiers, Hugo J. .
NATURE NEUROSCIENCE, 2017, 20 (11) :1504-1513
[10]   The Influence of Categories on Perception: Explaining the Perceptual Magnet Effect as Optimal Statistical Inference [J].
Feldman, Naomi H. ;
Griffiths, Thomas L. ;
Morgan, James L. .
PSYCHOLOGICAL REVIEW, 2009, 116 (04) :752-782