VikPath: A Vision Kansformer Framework for Effective Obstacle Avoidance in Self-Supervised Pathfinding
2026-08-24 • Robotics
Robotics
AI summaryⓘ
The authors address the challenge of finding paths in complex environments full of obstacles. They note that traditional methods rely on fixed rules and that existing learning methods depend on labeled examples, which can limit their effectiveness. Their new system, called Design, learns about obstacles without needing labeled data and aims to create paths that are not only short but also keep a safe distance from obstacles and stay smooth. Tests show that Design produces safer paths faster than current top methods. This approach could help robots or AI navigate more reliably in difficult spaces.
pathfindingheuristic algorithmsA* algorithmself-supervised learningobstacle clearancetrajectory smoothnessVision Kansformersharp-turn penaltyinference latencyautonomous navigation
Authors
Junyao Wang, Yulin Xu, Mohammad Abdullah Al Faruque
Abstract
Pathfinding is a fundamental problem in artificial intelligence and autonomous systems. Traditional heuristic-based algorithms, such as A*, rely on predefined heuristic functions to guide the search process. Although effective in structured environments, their search efficiency can degrade substantially in complex, obstacle-rich scenarios, where handcrafted heuristics may provide limited guidance. Recent studies have explored learning-based approaches to improve pathfinding efficiency; however, most existing methods rely on supervised learning and require labels generated by conventional planners or obtained through manual annotation. As a result, their performance is inherently influenced by the quality of the underlying supervision and may degrade when the labeling heuristics fail to capture complex environmental structures. Moreover, existing methods primarily optimize for path length while paying limited attention to obstacle clearance and trajectory smoothness, which can lead to paths that are difficult or unsafe to execute in real-world environments. To address these limitations, we propose $\Design$, a self-supervised pathfinding framework that jointly considers obstacle proximity and path smoothness. At its core, our novel \textit{Vision Kansformer} module learns representations of obstacle distributions without relying on labeled trajectories, enabling the model to better adapt to complex environments. We further introduce a sharp-turn penalty to encourage smoother and more practically executable paths. Extensive experiments demonstrate that, compared with state-of-the-art (SOTA) approaches, $\Design$ achieves an average of 3.28\% greater obstacle clearance and 87.07\% lower inference latency while maintaining smooth path generation.