Visuomotor Navigation for Embodied Robots With Spatial Memory and Semantic Reasoning Cognition

The fundamental prerequisite for embodied agents to make intelligent decisions lies in autonomous cognition. Typically, agents optimize decision-making by leveraging extensive spatiotemporal information from episodic memory. Concurrently, they utilize long-term experience for task reasoning and foster conscious behavioral tendencies. However, due to the significant disparities in the heterogeneous modalities of these two cognitive abilities, existing literature falls short in designing effective coupling mechanisms, thus failing to endow robots with comprehensive intelligence. This article introduces a navigation framework, the hierarchical topology-semantic cognitive navigation (HTSCN), which seamlessly integrates both memory and reasoning abilities within a singular end-to-end system. Specifically, we represent memory and reasoning abilities with a topological map and a semantic relation graph, respectively, within a unified dual-layer graph structure. Additionally, we incorporate a neural-based cognition extraction process to capture cross-modal relationships between hierarchical graphs. HTSCN forges a link between two different cognitive modalities, thus further enhancing decision-making performance and the overall level of intelligence. Experimental results demonstrate that in comparison to existing cognitive structures, HTSCN significantly enhances the performance and path efficiency of image-goal navigation. Visualization and interpretability experiments further corroborate the promoting role of memory, reasoning, as well as their online learned relationships, on intelligent behavioral patterns. Furthermore, we deploy HTSCN in real-world scenarios to further verify its feasibility and adaptability.

An algorithm to create model file for Partially Observable Markov Decision Process for mobile robot path planning

The Partially Observable Markov Decision Process (POMDP), a mathematical framework for decision-making in uncertain environments suffers from the curse of dimensionality. There are various methods that can handle huge sizes of POMDP matrices to create approximate solutions, but no serious effort has been reported to effectively control the size of the POMDP matrices. Manually creating the high-dimension matrices of a POMDP model is a cumbersome and sometimes even impossible task. The PCMRPP (POMDP file Creator for Mobile Robot Path Planning) software package implements a novel algorithm to programmatically generate these matrices such that: •The sizes of the matrices can be controlled by configuring the granularity of discretization of the components of the state and•The sparseness of the matrices can be controlled by configuring the spread of the observation probability distribution. This kind of flexibility allows one to achieve a trade-off between time complexity and the level of robustness of the POMDP solution.

Hierarchical framework for mobile robots to effectively and autonomously explore unknown environments

Achieving efficient and safe autonomous exploration in unknown environments is an urgent challenge to be overcome in the field of robotics. Existing exploration methods based on random and greedy strategies cannot ensure that the robot moves to the unknown area as much as possible, and the exploration efficiency is not high. In addition, because the robot is located in an unknown environment, the robot cannot obtain enough information to process the surrounding environment and cannot guarantee absolute safety. To improve the efficiency and safety of exploring unknown environments, we propose an autonomous exploration motion planning framework that is divided into the exploration and obstacle avoidance levels. The two levels are independent and interconnected. The exploration level finds the optimal frontier target point in the global scope based on the forward filtering angle and cost function, attracting the robot to move to the unknown area as much as possible, and improving the exploration efficiency; the obstacle avoidance level establishes a scenario-speed conversion mechanism, and the target point and obstacle information are weighed to realise dynamic motion planning and completes obstacle avoidance control, and ensures the safety of exploration. Experiments in different simulation scenarios and real environments verify the superiority of the method. Results show that our method is superior to the existing methods.