Edge Radar Material Classification Under Geometry Shifts
Authors: Jannik Hohmann, Dong Wang, Andreas Nüchter
Organizations: Department of Informatics XVII (Robotics), Julius-Maximilians-University Würzburg, 97074 Würzburg, Germany. · Zentrum für Telematik e.V., Würzburg · U2IS, ENSTA, Institut Polytechnique de Paris, France.
Material awareness can improve robotic navigation and interaction, particularly in conditions where cameras and LiDAR degrade. We present a lightweight mmWave radar material classification pipeline designed for ultra-low-power edge devices (TI IWRL6432), using compact range-bin intensity descriptors and a Multilayer Perceptron (MLP) for real-time inference. While the classifier reaches a macro-F1 of 94.2% under the nominal training geometry, we observe a pronounced performance drop under realistic geometry shifts, including sensor height changes and small tilt angles. These perturbations induce systematic intensity scaling and angle-dependent radar cross section (RCS) effects, pushing features out of distribution and reducing macro-F1 to around 68.5%. We analyze these failure modes and outline practical directions for improving robustness with normalization, geometry augmentation, and motion-aware features.
Figures & tables
Fig. 1 : Default experimental setup used for baseline data acquisition. The radar is mounted in a nadir-facing configuration at H=45 cm and θ=90∘ relative to the material surface.
Fig. 2 : Confusion matrix of the MLP classifier under nominal conditions ( H=45 cm, θ=90∘ ). Diagonal entries indicate per-class recall.
Fig. 3 : Confidence (maximum Softmax probability) distribution under nominal geometry.
Fig. 4 : Confusion matrix under height variations (35 cm and 55 cm). Off-diagonal density increases due to distance-dependent power changes.
Fig. 5 : Confidence distribution under geometry shifts (tilt). Increased low-confidence predictions indicate reduced certainty under OOD geometry.
Fig. 6 : Confusion matrix for “similar but unknown” data at nominal geometry ( H=45 cm, θ=90∘ ). Increased confusion indicates session-level sensitivity despite unchanged geometry.
Fig. 7 : Confidence distribution for “similar but unknown” data at nominal geometry. The probability mass shifts toward lower confidence compared to the baseline.
Accurate material recognition is a fundamental capability for intelligent perception systems to interact safely and effectively with the physical world. For instance, distinguishing visually similar objects like glass and plastic cups is critical for safety but challenging for vision-based methods due to specular reflections, transparency, and visual deception. While millimeter-wave (mmWave) radar offers robust material sensing regardless of lighting, existing camera-radar fusion methods are limited to closed-set categories and lack semantic interpretability. In this paper, we introduce VLMaterial, a training-free framework that fuses vision-language models (VLMs) with domain-specific radar knowledge for physics-grounded material identification. First, we propose a dual-pipeline architecture: an optical pipeline uses the segment anything model and VLM for material candidate proposals, while an electromagnetic characterization pipeline extracts the intrinsic dielectric constant from radar signals via an effective peak reflection cell area (PRCA) method and weighted vector synthesis. Second, we employ a context-augmented generation (CAG) strategy to equip the VLM with radar-specific physical knowledge, enabling it to interpret electromagnetic parameters as stable references. Third, an adaptive fusion mechanism is introduced to intelligently integrate outputs from both sensors by resolving cross-modal conflicts based on uncertainty estimation. We evaluated VLMaterial in over 120 real-world experiments involving 41 diverse everyday objects and 4 typical visually deceptive counterfeits across varying environments. Experimental results demonstrate that VLMaterial achieves a recognition accuracy of 96.08%, delivering performance on par with state-of-the-art closed-set benchmarks while eliminating the need for extensive task-specific data collection and training.
Jiangyou Zhu, He Chen
Department of Inforation Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
Millimeter-wave (mmWave) radar perception is limited by data scarcity: models trained on existing radar datasets fail to generalize to new objects, environments, and sensing trajectories. We present RadarTwin, a framework for generating deployment-specific radar training data before real data collection. Given a 3D reconstruction of a target space (phone LiDAR, robot-mounted sensing, or RGB-to-3D), RadarTwin uses a vision-language model to infer radar-relevant surface materials and a physics-based ray tracer to synthesize raw frequency-modulated continuous-wave (FMCW) radar measurements with multi-bounce propagation. To study what transfers from simulation to reality, we collect a paired real-simulated dataset spanning household objects, material classes, distances, rotations, translations, and mobile sensing trajectories. We show that simulated and real radar share the same object-discriminative shape and material features, and that modeling the environment's multipath is essential to matching real measurements. A representation trained on simulation alone recognizes real objects at 2.5 times chance with no real radar labels, and a few labeled examples raise this to 95.3% on a 12-way recognition task. RadarTwin enables training radar perception for a new space before any real radar data is collected there.
Emily Bejerano, Federico Tondolo, Devang Gupta +5
Columbia University New York, NY, USA · University of California, Merced Merced, CA, USA
Cameras and LiDAR degrade in rain, fog, and snow, while millimeter-wave radar remains largely unaffected. We align a radar encoder to frozen SigLIP vision embeddings and decode structured scene captions through a frozen vision-language model (VLM) with approximately 7M trainable parameters. On K-RADAR with held-out fog, light snow, and heavy snow sequences, all radar configurations outperform a camera baseline that collapses to over 90% hallucination. We identify a token-norm mismatch as the dominant failure mode when bridging radar to a frozen VLM and show that projector-output LayerNorm resolves it. Analysis of encoder complexity, caption format, and pooling strategy reveals tradeoffs that inform future radar-VLM pipeline design.
Kali Hamilton, Christoffer Heckman
Autonomous Robotics and Perception Group at the University of Colorado Boulder, Boulder, CO 80309, USA.