TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks
2026-08-03 • Robotics
RoboticsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed TravKAN, a new method that helps robots figure out if they can safely move over different terrains by using an understandable and fast model. Unlike typical deep learning methods, TravKAN breaks complex decisions into simple parts that can be clearly explained. They also introduced new features based on LiDAR reflectivity, which helps the robot better understand surface materials, something not often used before. Their tests show TravKAN works well and runs quickly, making it useful for robots that need clear, reliable, and fast terrain decisions.
Traversability analysisAutonomous robotsKolmogorov-Arnold NetworkLiDAR reflectivityFeature engineeringInterpretable machine learningGradient-boosted treesDeep neural networksSymbolic regressionReal-time computation
Authors
Daniel Fusaro, Simone Mosco, Wanmeng Li, Alberto Pretto
Abstract
Traversability analysis is a fundamental capability for autonomous mobile robots operating in unstructured environments. While modern machine learning approaches such as deep neural networks and gradient-boosted trees achieve strong predictive performance, they lack interpretability and provide limited insight into the underlying terrain-robot interaction dynamics. In this paper, we propose TravKAN, a Kolmogorov-Arnold Network-based framework for fast, scalable, and interpretable traversability estimation. TravKAN represents multivariate decision functions through compositions of learnable univariate functions, enabling compact architectures and symbolic extraction of analytic expressions after training. In addition, we introduce a novel set of handcrafted features derived from the reflectivity channel of LiDAR sensors. To the best of our knowledge, reflectivity has not been systematically exploited for handcrafted traversability descriptors, despite its potential to capture material and surface properties complementary to geometric cues. We evaluate TravKAN on public, real-world urban and off-road datasets and compare it against strong baselines. TravKAN achieves strong performance across all metrics, outperforming conventional deep models and approaching the performance of XGBoost. TravKAN-Lite, i.e., TravKAN's symbolic representation, reveals meaningful nonlinear feature interactions and provides a compact, deployment-friendly, and fast analytic model. Ablation studies further show the robustness of our method to architectural variations and quantify the contribution of the proposed reflectivity-based features. These properties make TravKAN attractive for robotic systems requiring transparency, real-time computational efficiency, and interpretability in safety-critical decision-making.