WiFi Channel State Information (CSI) enables fine-grained sensing of spatial relationships between wireless devices. The WiFi Sensor for Robotics (WSR) toolbox demonstrated that WiFi-CSI measurements collected during robot motion, combined with odometry, can be used to synthesize virtual antenna arrays, enabling motion-induced bearing estimation in multi-robot experiments. However, deploying the WSR approach has remained challenging due to its limited integration with standard robotics tools and reliance on deprecated WiFi-CSI acquisition hardware. This work presents an open-source simulation framework that integrates the WSR sensing pipeline within the robotic simulator Gazebo. The framework generates synthetic WiFi-CSI measurements with realistic physical signal properties and leverages realistic robot motion required for motion-induced sensing and downstream localization. It further supports processing both simulated and real WiFi-CSI data for direct comparison and validation. Our aim is to make WSR-style sensing accessible as a modular sensing modality for robotic research. We validate our framework by comparing simulated and real-world experiments using TurtleBot3 robots, and demonstrate its use for bearing estimation and robot localization. This work lowers the barrier to entry for WiFi-CSI-based sensing in multi-robot systems and provides a foundation for integrating WiFi-CSI sensing with multi-modal perception for localization and coordination. All code and experimental details are publicly available at https://github.com/baharhaghighat/DARS_2026_Dijkstra_et_al
Figures & tables
Figure 1: Overview of the functionality of our simulation framework (green and orange) in parallel with that of the WSR toolbox (blue). The framework blocks in green involve implementations in MATLAB, Gazebo, and ROS and those in orange involve MATLAB. The WSR toolbox blocks in blue involve implementations in C++ and Python from Jadhav et al. (2022b) . Our simulation framework operates fully independently from the WSR toolbox software package as we directly implement its methods within MATLAB. Three steps are included in our framework: (i) simulating raw CSI and robot odometry data, (ii) computing phase using CSI data, and (iii) running Bartlett’s estimator and Levenberg–Marquardt algorithm to estimate robots’ relative bearing and position.
Figure 2: Creating a virtual antenna array by moving a single physical antenna element hosted on a mobile robot. This illustration shows (i) a circular virtual antenna array with a 30 cm radius and (ii) a transmitting node placed 4 m away to satisfy the far-field assumption considered in Jadhav et al. (2022a) .
Figure 3: We use TurtleBot3 Waffle robots in our simulation and real setups to collect data. (a) Real robot with onboard UP Squared SBC, Intel WL5300 NIC, and WiFi antenna. (b) Simulated robot with the WiFi antenna at the model’s center.
Figure 4: 3D view of the simulated experiment setup in Gazebo with an indication of the trajectories. The benchmark scenario matching the setup described in Jadhav et al. (2022b) only includes R1 to R4, while R5 and R6 are added in the experiments that follow. R4 and R5 are mobile while R1, R2, R3, and R6 are static beacons.
Figure 5: AoA profiles for R4 on a 2D circular trajectory, with yellow spots marking AoA peaks and crosshairs indicating true bearing. Figures in (a, c) show the connection to R3 (ground level, high noise), and in (b, d) to R6 (elevated, low noise). Calculations use odometry for (a, b) and true simulated positions for (c, d). R4’s purely 2D motion causes elevation ambiguity, resulting in mirrored estimations across the 90 ∘ trajectory plane.
Figure 6: AoA error density for random walk trajectories grouped by level of signal noise; R1 and R6 have an SNR of 30 and are classified to mimic LOS, where R2 and R3 have an SNR of 3, mimicking NLOS scenarios.
Indoor navigation to task-relevant targets remains difficult when the target is small, occluded, or visually indistinct. Meanwhile, smart appliances, mobile devices, and IoT tags emit Wi-Fi signals during everyday communication, providing a pervasive but underused spatial cue. We study visual-Wi-Fi navigation, where a robot reaches a signal-emitting device in an unmapped environment using onboard visual observations and Wi-Fi packets overheard from the device, without connecting to the device or modifying infrastructure. Realizing this requires pose-dependent Wi-Fi observations during closed-loop policy learning and reliable spatial cues from bearing measurements corrupted by indoor multipath propagation on a moving robot. We present WiFiSpaces, which extends the Habitat embodied simulator with online ray-traced Wi-Fi sensing, rendering Wi-Fi observations for a robot-mounted antenna array at continuous poses during policy rollouts. On top of it, we build ViFiNav, a localization-aware navigation framework: an online source-localization algorithm exploits robot motion to disambiguate and robustly aggregate bearings from multiple viewpoints into a confidence-aware source estimate, and a learned policy fuses this evolving estimate with depth observations and learns to act on it as it is refined. Experiments show that exploiting robot motion is key to accurate source estimates, and that fine-tuning on ray-traced Wi-Fi observations in WiFiSpaces improves the success rate of ViFiNav. The policy transfers zero-shot to unseen scene datasets, and we deploy it on a real robot with a Wi-Fi sensor built from a commodity router, without any real-world training.
We present LiveSense - a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into a centimeter-level Range-Doppler sensor while preserving simultaneous communication capability. The laptops are equipped with COTS Intel AX211 (Wi-Fi 6E) or Intel BE201 (Wi-Fi 7) NICs. LiveSense can (i) Extract fully-synchronized channel state information (CSI) at >= 40 Hz, (ii) Perform time-phase alignment and self-interference cancellation on-device, and (iii) Provide a real-time stream of range, Doppler, subcarrier magnitude/phase and annotated video frames to a Python/Qt Graphical User Interface (GUI). The demo will showcase the ability to detect (i) Distance and radial velocity of attendees within a few meters of the device, (ii) Micro-motion (respiration), and (iii) Hand-gesture ranging. To the best of our knowledge, this is the first-ever demo to obtain accurate range information of targets from commercial Wi-Fi, despite the limited 160 MHz bandwidth.
Jessica Sanson, Rahul C. Shah, Maximilian Pinaroc +2
∗ Intel Deutschland GmbH, Munich, Germany · † Intel Labs, Santa Clara, CA, USA
WiFi Channel State Information (CSI) enables privacy-preserving human pose sensing in camera-denied environments, but existing WiFi-based pose estimators often fail under environment shifts and rely on costly camera-based annotation pipelines that limit scale. We propose WiFi-JEPA, a self-supervised framework that learns CSI-native representations by predicting masked latent embeddings instead of reconstructing raw CSI signals that may contain hardware-specific artifacts. WiFi-JEPA makes three contributions: (i) CSI-specific tokenization and link masking tailored to the CSI tensor over channel, time, and link (C,T,L); masking entire Tx-Rx antenna links forces the model to predict one spatial link view from others, capturing cross-link correlations informative of 3D spatial structure. (ii) A ray-tracing CSI simulation pipeline that generates diverse unlabeled CSI from randomized geometric primitives, providing scalable pre-training data without pose annotations. (iii) State-of-the-art results on Person-in-WiFi-3D: WiFi-JEPA outperforms prior WiFi-CSI baselines on both single- and multi-person 3D pose estimation under the same evaluation protocol. We also show that simulated CSI provides complementary pre-training signal to real CSI, and that four vision-native SSL objectives degrade performance below training from scratch, whereas WiFi-JEPA consistently improves downstream pose estimation.
Doeon Kim, Jungyoon Lee, Seongsin Kim +1
Department of Intelligent Semiconductors, Soongsil University, Republic of Korea · Department of AI Convergence Security, Soongsil University, Republic of Korea · School of AI Software, Soongsil University, Republic of Korea