Robust and privacy-preserving indoor scene understanding remains a fundamental open problem.While optical sensors such as RGB and LiDAR offer high spatial fidelity, they suffer from severe occlusions and introduce privacy risks in indoor environments.In contrast, millimeter-wave (mmWave) radar preserves privacy and penetrates obstacles, but its inherently low spatial resolution makes reliable geometric reasoning difficult.We introduce RISE, the first benchmark and system for single-static-radar indoor scene understanding, jointly targeting layout reconstruction and object detection.RISE is built upon the key insight that multipath reflections—traditionally treated as noise—encode rich geometric cues.To exploit this, we propose a Bi-Angular Multipath Enhancement that explicitly models Angle-of-Arrival and Angle-of-Departure to recover secondary (ghost) reflections and reveal invisible structures.On top of these enhanced observations, a simulation-to-reality Hierarchical Diffusion framework transforms fragmented radar responses into complete layouts reconstruction and object detection.Our benchmark contains 50,000 frames collected across 100 real indoor trajectories, forming the first large-scale dataset dedicated to radar-based indoor scene understanding.Extensive experiments show that RISE reduces the Chamfer Distance by 60\% (down to 16 cm) compared to the state of the art in layout reconstruction, and delivers the first mmWave-based object detection, achieving 58\% IoU.These results establish RISE as a new foundation for geometry-aware and privacy-preserving indoor scene understanding using a single static radar.

We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our approach leverages millimeter-wave (mmWave) wireless signals, which can penetrate common occlusions and reflect off hidden objects. In contrast to past mmWave reconstruction methods, which suffer from limited coverage and high noise, Wave-Former introduces a physics-aware shape completion model capable of inferring full 3D geometry. At the heart of Wave-Former's design is a novel three-stage pipeline which bridges raw wireless signals with recent advancements in vision-based shape completion by incorporating physical properties of mmWave signals. The pipeline proposes candidate geometric surfaces, employs a transformer-based shape completion model designed specifically for mmWave signals, and finally performs entropy-guided surface selection. This enables Wave-Former to be trained using entirely synthetic point-clouds, while demonstrating impressive generalization to real-world data. In head-to-head comparisons with state-of-the-art baselines, Wave-Former raises recall from 54% to 72% while maintaining a high precision of 85%.

Underwater backscatter is a promising technology for ultra-low-power underwater networking, but existing systems break down in mobile scenarios. This paper presents EchoRider, the first system to enable reliable underwater backscatter networking under mobility. EchoRider introduces three key components. First, it incorporates a robust and energy-efficient downlink architecture that uses chirp-modulated transmissions at the reader and a sub-Nyquist chirp decoder on backscatter nodesbringing the resilience of LoRa-style signaling to underwater backscatter while remaining ultra-low-power. Second, it introduces a NACK-based full-duplex retransmission protocol, enabling efficient, reliable packet delivery. Third, it implements a Doppler-resilient uplink decoding pipeline that includes adaptive equalization, polar coding, and dynamic retraining to combat channel variation. We built a full EchoRider prototype and evaluated it across over 1,200 real-world mobile experiments. EchoRider improves bit error rate by over 125x compared to a state-of-the-art baseline and maintains underwater goodput of 0.8 kbps at speeds up to 2.91 knots. In contrast, the baseline fails at speeds as low as 0.17 knots. Finally, we demonstrate EchoRider in end-to-end deployments involving mobile drones and sensor nodes, showing its effectiveness in practical underwater networked applications.

The past few years have witnessed growing interest in millimeter wave (mmWave) based reconstruction in the mobile community [3, 5, 7, 14]. Unlike classical vision-based imaging systems, which are limited to line-of-sight, these mmWave-based systems can operate in through-occlusion scenarios, enabling them to sense objects in closed boxes and beneath clutter. This is because mmWave signals can traverse through many everyday occlusions (e.g., cardboard, fabric, etc.) [1, 11], and reflect off objects behind these occlusions, allowing them to produce images of the occluded objects. This capability, combined with the recent emergence of low-cost commercial mmWave radars, has the potential to enable many promising applications. For example, pick-and-place robots can leverage through-occlusion reconstructions to find and manipulate hidden objects, such as those beneath clutter or within a closed box. Similarly, Augmented Reality (AR) devices could leverage them to perceive occluded objects and display them to the user, truly augmenting our human perception. Smart home devices can use them for through-occlusion gesture recognition, to enable non-verbal commands even when users are hidden from view.

We present the design, implementation, and evaluation of MiNav, a system capable of accurate, efficient and fully autonomous drone navigation in challenging indoor environments, including those where vision-based systems fail. MiNav builds on recent literature in millimeter-wave (mmWave) backscatter localization and makes the leap to full end-to-end autonomous mmWave-based navigation. MiNav leverages a mmWave radar mounted on a drone and one or more mmWave backscatter tags deployed in the environment. To enable autonomous navigation, our design introduces key innovations. First, MiNav derives a novel Joint DOP-SNR formulation to probabilistically model uncertainty in localization, and uses this uncertainty to generate an RF-Navigation Map that maximizes the accuracy and reliability of mmWave backscatter localization throughout an environment. It then applies a RF-aware Autonomous Path Planning technique that jointly optimizes for navigation efficiency and localization performance. We built an end-to-end real-time implementation of MiNav consisting of a custom built drone and mmWave backscatter tags. We tested it in practical indoor environments. We run over 165 successful autonomous missions across different tag deployments and demonstrate a median 3D navigation error of 9.1 cm. Our results also show that in comparison to baseline implementations that rely on more classical uncertainty metrics, MiNav achieves a 20% increase in navigation reliability and nearly 3x improvement in self-tracking in millimeter-wave backscatter localization. Finally, we demonstrate first of its kind capabilities, such as fully autonomous, end-to-end mmWave-based drone navigation and path planning in featureless and dark environments. Demo video: http://y2u.be/EpnWibRcxBI

We present the design, implementation, and evaluation of MiFly, a self-localization system for autonomous drones that works across indoor and outdoor environments, including low-visibility, dark, and GPS-denied settings. MiFly performs 6DoF self-localization by leveraging a single millimeter-wave (mmWave) anchor in its vicinity - even if that anchor is visually occluded. MiFly's core contribution is in its joint design of a mmWave anchor and localization algorithm. The low-power anchor features a novel dual-polarization dual-modulation architecture, which enables single-shot 3D localization. MmWave radars mounted on the drone perform 3D localization relative to the anchor and fuse this data with the drone's internal inertial measurement unit (IMU) to estimate its 6DoF trajectory. We implemented and evaluated MiFly on a DJI drone. We collected over 6,600 localization estimates across different trajectory patterns and demonstrate a median localization error of 7 cm and a 90th percentile less than 15 cm, even in low-light conditions and when the anchor is fully occluded (visually) from the drone. Demo video: youtu.be/LfXfZ26tEok

This demo presents BlueTag, a permanently deployed underwater sensor system based on backscatter communication. BlueTag is a battery-powered CTD (conductivity, temperature, depth) sensor that transmits measurements every 15 minutes to a remote base station via underwater backscatter. The base station archives these measurements and publishes them online. Unlike prior underwater backscatter systems limited to short-term laboratory experiments, BlueTag has been deployed in the Charles River in Boston, MA since July 9th, 2025, marking the first long-term underwater backscatter deployment of its kind to sense meaningful environmental data. Live data from this deployment is available publicly at https://sk-exp-server.mit.edu/.

The ability to observe the world is fundamental to reasoning and making informed decisions on how to interact with the environment. However, optical perception can often be disrupted due to common occurrences, such as occlusions, which can pose challenges to existing vision systems. We present MITO, the first millimeter-wave (mmWave) dataset of diverse, everyday objects, collected using a UR5 robotic arm with two mmWave radars operating at different frequencies and an RGB-D camera. Unlike visible light, mmWave signals can penetrate common occlusions (e.g., cardboard boxes, fabric, plastic) but each mmWave frame has much lower resolution than typical cameras. To capture higher-resolution mmWave images, we leverage the robot's mobility and fuse frames over the synthesized aperture. MITO captures over 24 million mmWave frames and uses them to generate 550 high-resolution mmWave (synthetic aperture) images in line-of-sight and non-light-of-sight (NLOS), as well as RGB-D images, segmentation masks, and raw mmWave signals, taken from 76 different objects. We develop an open-source simulation tool that can be used to generate synthetic mmWave images for any 3D triangle mesh. Finally, we demonstrate the utility of our dataset and simulator for enabling broader NLOS perception by developing benchmarks for NLOS segmentation and classification.

Underwater backscatter is an emerging technology for ultra-low-power communication and networking. Unlike traditional underwater acoustical modems, which communicate by generating their own acoustical signals, underwater backscatter nodes communicate by reflecting external acoustical signals, enabling them to operate at 5-6 orders of magnitude less power than existing low-power modems. Yet, before the practical adoption of this technology, it remains necessary to understand its link budget in practical ocean channels. In this article, we perform a comprehensive investigation of the underwater backscatter link budget in practical channels considering various sources of signal and noise that are unique to backscatter communication systems. We develop a closed-form end-to-end link-budget model of underwater backscatter and perform experimental validations in real-world environments. For the first time, we experimentally verify the end-to-end analytical model of the signal-to-noise ratio (SNR) as a function of distance and source level. Not only does this model enable us to predict the expected SNR within a median of 0.75 dB of the experimentally measured one, but also to identify new methods that improve the performance of underwater backscatter and extend its range over state-of-the-art past work. We then use this validated model to simulate backscatter performance under practical ocean channels and understand the impact of system and environmental parameters on the end-to-end performance. By developing and validating the link budget model, this article paves the way for the practical adoption of underwater backscatter in applications of ocean climate change monitoring, scientific studies, and coastal resilience.

Localization is a critical task for underwater robots, yet today's underwater localization systems are limited by their accuracy, scalability, and/or energy consumption (i.e., longevity). We present the design, implementation, and evaluation of EchoBLUE- an accurate, scalable, and low-power localization system for underwater robots. In EchoBLUE, an underwater robot transmits SONAR-style (FMCW) signals, and leverages ultra-low power underwater backscatter nodes as location anchors. EchoBLUE's design introduces two key innovations. The first is a novel doppler compensation mechanism that enables it to accurately self-localize under mobility: the technique employs a cross-chirp mechanism that exploits the quad-band nature of the resulting backscatter response to overcome the range-doppler ambiguity. Second, it introduces the first semi-active retrodirective underwater backscatter design and uses it for location anchors; this design achieves wide bandwidth to backscatter the full FMCW signal, enabling fine-grained localization. We implemented a proof of concept prototype of EchoBLUE by building a base station mounted on a BlueROV2 underwater robot and custom-designed low-power retrodirective location anchors deployed in a pool. Our evaluation across 700 real-world trials demonstrates that EchoBLUE achieves a median 3D localization accuracy of 28 cm and 90th percentile of 48 cm. Moreover, these anchors consume only 740 mu W for semi-active backscatter, paving the way for truly low-power and scalable underwater localization.

We present the design, implementation, and evaluation of Ceilbot, a ceiling-mounted robot for efficient and accurate RFID localization. Unlike previous robotic RFID localization systems, which focused primarily on localization accuracy, Ceilbot learns to jointly optimize both the accuracy and speed of localization. To achieve this, we introduce a reinforcement-learning-based (RL) trajectory optimization network that determines the most effective trajectory for a robot-mounted reader antenna. Our algorithm integrates aperture length, estimated tag locations, and location confidence (using a wideband synthetic-aperture-radar formulation) into the state observations to learn the optimal trajectory. We developed an end-to-end prototype of Ceilbot and evaluated it in a practical stockroom-like environment. The prototype includes a standard RFID reader with our custom hardware extension (to enable wideband localization of off-the-shelf RFIDs) and a ceiling robot that moves on a 2D track. In our evaluation, Ceilbot demonstrated a median 3D localization accuracy of 0.17 meters and located over 50 RFID tags 12.5x faster than the state-of-the-art baseline. Our results highlight the potential for RL-based RFID localization to significantly enhance the efficiency of RFID inventory processes across sectors such as manufacturing, retail, and logistics.

This paper presents the design, implementation, and evaluation of mmNorm, a new and highly-accurate method for non-line-of-sight 3D object reconstruction using millimeter wave (mmWave) signals. In contrast to past approaches for millimeter-wave-based imaging that perform backprojection for 3D object reconstruction, mmNorm reconstructs the surface by estimating the object's surface normals. To do this, it introduces a novel algorithm that directly estimates the surface normal vector field from mmWave reflections. By then inverting the normal field, it can reconstruct structural isosurfaces, then solve for the exact surface through a novel mmWave optimization framework. We built an end-to-end prototype of mmNorm using a TI IWR1443 Boost mmWave radar and a UR5e Robotic Arm, and evaluated it in over 110 real-world experiments across more than 60 different everyday objects. In a head-to-head comparison with state-of-the-art baselines, mmNorm achieves 96% reconstruction accuracy (3D F-score) compared to 78% for the best-performing baseline. These results show that mmNorm is capable of high-accuracy mmWave object reconstruction. The codebase and a video demonstration are available here: https://github.com/signalkinetics/mmNorm

We present the design, implementation, and evaluation of 3D-BLUE, an ultra-low-power underwater 3D localization system that can be deployed on compact robots to accurately localize them in shallow underwater environments. 3D-BLUE's design introduces two core components. First, it adapts a recent ultra-low-power underwater acoustic communication technology (called piezo-electric backscatter) to the underwater robotics localization problem; specifically, it integrates backscatter nodes into the underwater robot and uses them for localizing it. Second, it leverages the physical properties of the backscatter technology to efficiently extract spatio-temporal-spectral features from the backscatter signal; using these features, it devises a particle-filter-based algorithm to localize the corresponding robot accurately in challenging shallow-water environments. We implemented an end-to-end prototype of 3D-BLUE on a BlueROV2 robot and custom-built backscatter localization system, and evaluated it in dozens of experimental trials in a pool. Our results demonstrate that 3D-BLUE can localize the robot with an accuracy of around 0.25m at close range and an accuracy of around 1.4m at a range of 10m. This high localization accuracy opens important commercial, naval, and environmental applications in challenging shallow-water environments such as shores, rivers, pools, and narrow waterways.

We present RL2, a robotic system for efficient and accurate localization of UHF RFID tags. In contrast to past robotic RFID localization systems, which have mostly focused on location accuracy, RL2 learns how to jointly optimize the accuracy and speed of localization. To do so, it introduces a reinforcement-learning-based (RL) trajectory optimization network that learns the next best trajectory for a robot-mounted reader antenna. Our algorithm encodes the aperture length and location confidence (using a synthetic-aperture-radar formulation) from multiple RFID tags into the state observations and uses them to learn the optimal trajectory. We built an end-to-end prototype of RL2 with an antenna moving on a ceiling-mounted 2D robotic track. We evaluated RL2 and demonstrated that with the median 3D localization accuracy of 0.55m, it locates multiple RFID tags 2.13x faster compared to a baseline strategy. Our results show the potential for RL-based RFID localization to enhance the efficiency of RFID inventory processes in areas spanning manufacturing, retail, and logistics.