<p>Recently, the brain-inspired mechanisms beneficial to efficient navigation in mammals have exhibited huge research potential. Specifically, the geometry cell model has shown significant insights into the ability of mammals, which is used to model the geometric information of their surroundings during movement. Meanwhile, the process of general exploration will consume large amounts of computing resources when agents with high-performance computing equipment accomplish autonomous tasks. This paper focuses on the long-range autonomous exploration and navigation tasks in which they are conducted by agents within complex indoor and outdoor environments. To reduce the computational demands, we propose a framework integrating the Brain-Inspired Geometry-awareness namely BIG for two autonomous tasks. The exploration task named BIG-Explorer involves efficiently searching untouched areas by embedding the geometry cell model. It identifies expanding frontiers using geometric assigners and takes into account relevant factors such as boundary information. The navigation task named BIG-Navigator builds upon insights gained during the exploration phase and guides agents to a predefined destination. We conduct comprehensive experimental assessments within third-party simulation environments. The evaluation metrics employed in this paper include the number of nodes, the length of a path, algorithm execution time, and the size of exploration space. Finally, the results of the evaluation demonstrate that the incorporation of geometry cell model increases the efficiency in both exploration and navigation processes by at least <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="43020_2024_156_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(20\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>20</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation>, compared with four benchmark methods.</p>

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

BIG: a framework integrating brain-inspired geometry cell for long-range exploration and navigation

  • Zhen Sun,
  • Kehui Ma,
  • Songpengcheng Xia,
  • Qi Wu,
  • Chaoran Xiong,
  • Yan Xiang,
  • Ling Pei

摘要

Recently, the brain-inspired mechanisms beneficial to efficient navigation in mammals have exhibited huge research potential. Specifically, the geometry cell model has shown significant insights into the ability of mammals, which is used to model the geometric information of their surroundings during movement. Meanwhile, the process of general exploration will consume large amounts of computing resources when agents with high-performance computing equipment accomplish autonomous tasks. This paper focuses on the long-range autonomous exploration and navigation tasks in which they are conducted by agents within complex indoor and outdoor environments. To reduce the computational demands, we propose a framework integrating the Brain-Inspired Geometry-awareness namely BIG for two autonomous tasks. The exploration task named BIG-Explorer involves efficiently searching untouched areas by embedding the geometry cell model. It identifies expanding frontiers using geometric assigners and takes into account relevant factors such as boundary information. The navigation task named BIG-Navigator builds upon insights gained during the exploration phase and guides agents to a predefined destination. We conduct comprehensive experimental assessments within third-party simulation environments. The evaluation metrics employed in this paper include the number of nodes, the length of a path, algorithm execution time, and the size of exploration space. Finally, the results of the evaluation demonstrate that the incorporation of geometry cell model increases the efficiency in both exploration and navigation processes by at least \(20\%\) 20 % , compared with four benchmark methods.