Learning Agent Interactions from Density Evolution in 3D Regions With Obstacles

被引:0
|
作者
Tirumalai, Amoolya [1 ,2 ]
Mavridis, Christos N. [1 ,2 ]
Baras, John S. [1 ,2 ]
机构
[1] Univ Maryland, Dept Elect & Comp Engn, College Pk, MD 20742 USA
[2] Univ Maryland, Inst Syst Res, College Pk, MD 20742 USA
来源
2023 62ND IEEE CONFERENCE ON DECISION AND CONTROL, CDC | 2023年
关键词
PARTICLE; BEHAVIORS; ENSEMBLE; DYNAMICS; SCHEMES; SYSTEMS; ORDER;
D O I
10.1109/CDC49753.2023.10384269
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this work, we study the inverse problem of identifying complex flocking dynamics in a domain cluttered with obstacles. We get inspiration from animal flocks moving in complex ways with capabilities far beyond what current robots can do. Owing to the difficulty of observing and recovering the trajectories of the agents, we focus on the dynamics of their probability densities, which are governed by partial differential equations (PDEs), namely compressible Euler equations subject to non-local forces. We formulate the inverse problem of learning interactions as a PDE-constrained optimization problem of minimizing the squared Hellinger distance between the histogram of the flock and the distribution associated to our PDEs. The numerical methods used to efficiently solve the PDE-constrained optimization problem are described. Realistic flocking data are simulated using the Boids model of flocking agents, which differs in nature from the reconstruction models used in our PDEs. Our analysis and simulated experiments show that the behavior of cohesive flocks can be recovered accurately with approximate PDE solutions.
引用
收藏
页码:7156 / 7161
页数:6
相关论文
共 50 条
  • [41] Toward Autonomous Intelligence: From Active 3D Vision to Invariant Object and Scene Learning, Recognition, and Search
    Grossberg, Stephen
    ADVANCES IN COGNITIVE NEURODYNAMICS (V), 2016, : 17 - 25
  • [42] 3D Modeling of interactions between Jupiter's ammonia clouds and large anticyclones
    Palotai, Csaba
    Dowling, Timothy E.
    Fletcher, Leigh N.
    ICARUS, 2014, 232 : 141 - 156
  • [43] Micromechanical Strength Modeling and Investigation of Stitch Density Effects on 3D Orthogonal Composites
    Karkkainen, Ryan L.
    Tzeng, Jerome T.
    JOURNAL OF COMPOSITE MATERIALS, 2009, 43 (25) : 3125 - 3142
  • [44] Global solution to the 3D inhomogeneous nematic liquid crystal flows with variable density
    Hu, Xianpeng
    Liu, Qiao
    JOURNAL OF DIFFERENTIAL EQUATIONS, 2018, 264 (08) : 5300 - 5332
  • [45] A dislocation-density-based 3D crystal plasticity model for pure aluminum
    Alankar, Alankar
    Mastorakos, Ioannis N.
    Field, David P.
    ACTA MATERIALIA, 2009, 57 (19) : 5936 - 5946
  • [46] Electron Tomography: From 3D Statics to 4D Dynamics
    Su, Dang Sheng
    ANGEWANDTE CHEMIE-INTERNATIONAL EDITION, 2010, 49 (50) : 9569 - 9571
  • [47] Heterogeneous Features Fusion with Collaborative Representation Learning for 3D Action Recognition
    Liang, Chengwu
    Chen, Enqing
    Qi, Lin
    Guan, Ling
    2017 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2017, : 162 - 168
  • [48] Learning Optimal Impedance Control During Complex 3D Arm Movements
    Naceri, Abdeldjallil
    Schumacher, Tobias
    Li, Qiang
    Calinon, Sylvain
    Ritter, Helge
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) : 1248 - 1255
  • [49] Error-Insensitive 3D Entanglement Gate with Optimal Control of Geometric Evolution
    Niu, Wei
    Wu, Jin-Lei
    Wang, Pan
    Ji, Xin
    ANNALEN DER PHYSIK, 2021, 533 (08)
  • [50] A 3D forward stratigraphic model of aeolian dune evolution for prediction of lithofacies heterogeneity
    Yan, Na
    Colombera, Luca
    Cosgrove, Grace I. E.
    Mountney, Nigel P.
    COMPUTERS & GEOSCIENCES, 2024, 187