Abstract
In the last few years, several research activities were devoted to the exploration of the potential of advanced technology—such as artificial intelligence techniques—to enhance the performance of navigation systems for land, air, and sea vehicles. Among the various AI techniques, we focused in particular on heuristic search and case-based reasoning. We explored the impact of these AI techniques in two different contexts of vehicle navigation systems. In the first context, we developed a hierarchical control system that adopts an onboard AI-enhanced decision-making process in order to select the most appropriate control level during the autonomous navigation of an unmanned mobile robot in a previously unknown environment. By integrating case-based reasoning with a combination of algorithms, it derives from the stored information about past executions of test runs a suitable vehicle control scheme based on a multilevel strategic, tactical, and reactive architecture. The system provides fully autonomous navigation in the presence of movable obstacles and uncertainty of external reference points. We implemented, tested, and evaluated the performance of the hierarchical control system on a simulation of the operation of an autonomous warehousing vehicle moving in real working conditions. In the second context, we developed an autonomous vehicle guidance system, based on a combination of AI and GIS techniques, to guide, using wheel encoders and a compass as unique sources of information, a land vehicle moving in a landmark environment to a target point specified by means of a natural language dialogue interface. Using a region and point-based mapping process, the system constructs, upon user request, a self-updating ground map with Euclidean coordinates of the configuration of the landmarks and known reference points, and an associated weighted visibility graph, which allows the system to reason about the macro and micro plans. The macro and micro plans are used at the crew station level in the algorithm behavior, while the fuzzy multisensor fusion level, which is integrated into the system, merges compass and wheel encoder data to detect the occurrence of sensor fault events and to establish the order of priority for the goals to be satisfied during the vehicle movements.
References
Tamanampudi, Venkata Mohit. "Automating CI/CD Pipelines with Machine Learning Algorithms: Optimizing Build and Deployment Processes in DevOps Ecosystems." Distributed Learning and Broad Applications in Scientific Research 5 (2019): 810-849.
Singh, Jaswinder. "Deepfakes: The Threat to Data Authenticity and Public Trust in the Age of AI-Driven Manipulation of Visual and Audio Content." Journal of AI-Assisted Scientific Discovery 2.1 (2022): 428-467.
Machireddy, Jeshwanth Reddy. "Revolutionizing Claims Processing in the Healthcare Industry: The Expanding Role of Automation and AI." Hong Kong Journal of AI and Medicine 2.1 (2022): 10-36.
S. Kumari, “Kanban-Driven Digital Transformation for Cloud-Based Platforms: Leveraging AI to Optimize Resource Allocation, Task Prioritization, and Workflow Automation”, J. of Artificial Int. Research and App., vol. 1, no. 1, pp. 568–586, Jan. 2021
Tamanampudi, Venkata Mohit. "AI and DevOps: Enhancing Pipeline Automation with Deep Learning Models for Predictive Resource Scaling and Fault Tolerance." Distributed Learning and Broad Applications in Scientific Research 7 (2021): 38-77.