Research
At RoMA, our research focuses on developing foundation models for next-generation robotics. Our work spans multiple domains including computer vision, SLAM, sensor fusion, and deep learning.
Highlighted
Decoupling the Declarative from the Procedural in Vision-Language-Action Models
arXiv
·
01 Jan 2026
·
doi:10.48550/arXiv.2606.21496
A modular Vision-Language-Action architecture that separates semantic (what/where) understanding from procedural (how) execution, improving zero-shot generalization of robot skills to novel objects.
Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse
CoRR
·
15 Jun 2025
·
doi:10.48550/arXiv.2506.07639
Efficient embodied reasoning through thought reuse, enabling faster decision-making in robotic applications.
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
NeurIPS
·
22 May 2024
·
doi:10.48550/arXiv.2405.14014
A novel approach for robust 3D occupancy prediction using 4D imaging radar, advancing autonomous driving perception in challenging conditions.
Self-adapting Large Visual-Language Models to Edge Devices Across Visual Modalities
ECCV 2024
·
29 Sep 2024
·
doi:10.1007/978-3-031-73390-1_18
Adapting large vision-language models for efficient deployment on edge devices across different visual modalities.
All
2026
Automating Model Deployment on Mobile Devices
Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services Workshops
·
20 Jun 2026
·
doi:10.1145/3812836.3814754
mmWave Radar Perception Learning Using Pervasive Visual-Inertial Supervision
IEEE Transactions on Intelligent Transportation Systems
·
01 Jun 2026
·
doi:10.1109/TITS.2026.3659202
One Workflow Doesn't Fit All: Adaptive Workflows for Edge AI Development
GetMobile: Mobile Computing and Communications
·
23 Apr 2026
·
doi:10.1145/3810919.3810921
Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin
arXiv
·
01 Jan 2026
·
doi:10.48550/arXiv.2603.18026
2025
VISC: mmWave Radar Scene Flow Estimation using Pervasive Visual-Inertial Supervision
2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
19 Oct 2025
·
doi:10.1109/IROS60139.2025.11246830
ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Images
Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems
·
06 May 2025
·
doi:10.1145/3715014.3722058
Risk Controlled Image Retrieval
Proceedings of the AAAI Conference on Artificial Intelligence
·
11 Apr 2025
·
doi:10.1609/aaai.v39i26.34931
Learning Selective Sensor Fusion for State Estimation
IEEE Transactions on Neural Networks and Learning Systems
·
01 Mar 2025
·
doi:10.1109/TNNLS.2022.3176677
M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
arXiv
·
01 Jan 2025
·
doi:10.48550/arXiv.2512.12378
Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
arXiv
·
01 Jan 2025
·
doi:10.48550/arXiv.2511.10762
The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
arXiv
·
01 Jan 2025
·
doi:10.48550/arXiv.2502.03270
2024
Deep Learning for Visual Localization and Mapping: A Survey
IEEE Transactions on Neural Networks and Learning Systems
·
01 Dec 2024
·
doi:10.1109/TNNLS.2023.3309809
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
Lecture Notes in Computer Science
·
03 Nov 2024
·
doi:10.1007/978-3-031-72691-0_12
Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
14 Oct 2024
·
doi:10.1109/IROS58592.2024.10801488
Forecasting backdraft with multimodal method: Fusion of fire image and sensor data
Engineering Applications of Artificial Intelligence
·
01 Jun 2024
·
doi:10.1016/j.engappai.2024.107939
Multimodal Indoor Localization Using Crowdsourced Radio Maps
2024 IEEE International Conference on Robotics and Automation (ICRA)
·
13 May 2024
·
doi:10.1109/ICRA57147.2024.10610683
Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation
2024 IEEE International Conference on Robotics and Automation (ICRA)
·
13 May 2024
·
doi:10.1109/ICRA57147.2024.10610775
RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud
2024 IEEE International Conference on Robotics and Automation (ICRA)
·
13 May 2024
·
doi:10.1109/ICRA57147.2024.10610368
End-to-End Target Liveness Detection via mmWave Radar and Vision Fusion for Autonomous Vehicles
ACM Transactions on Sensor Networks
·
11 May 2024
·
doi:10.1145/3628453
Introduction to the Special Section on Contact-free Smart Sensing in AIoT
ACM Transactions on Sensor Networks
·
11 May 2024
·
doi:10.1145/3639406
Robust Metric Localization in Autonomous Driving via Doppler Compensation With Single-Chip Radar
IEEE Transactions on Intelligent Transportation Systems
·
01 Jan 2024
·
doi:10.1109/TITS.2023.3305487
2023
Orientation-Aware 3D SLAM in Alternating Magnetic Field from Powerlines
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
·
19 Dec 2023
·
doi:10.1145/3631446
Poster Abstract: Multimodal Indoor Localization Using Crowdsourced Radio Maps
Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems
·
12 Nov 2023
·
doi:10.1145/3625687.3628398
Feature-based Visual Odometry for Bronchoscopy: A Dataset and Benchmark
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
01 Oct 2023
·
doi:10.1109/IROS55552.2023.10342034
RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Conditions
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
01 Oct 2023
·
doi:10.1109/IROS55552.2023.10341653
CubeLearn: End-to-End Learning for Human Motion Recognition From Raw mmWave Radar Signals
IEEE Internet of Things Journal
·
15 Jun 2023
·
doi:10.1109/JIOT.2023.3237494
Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
·
01 Jun 2023
·
doi:10.1109/CVPR52729.2023.00901
Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings
IEEE Robotics and Automation Letters
·
01 May 2023
·
doi:10.1109/LRA.2023.3256085
Human Parsing with Joint Learning for Dynamic mmWave Radar Point Cloud
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
·
27 Mar 2023
·
doi:10.1145/3580779
SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing
Patterns
·
01 Mar 2023
·
doi:10.1016/j.patter.2023.100703
Differentiable Radio Frequency Ray Tracing for Millimeter-Wave Sensing
arXiv
·
01 Jan 2023
·
doi:10.48550/arXiv.2311.13182
Risk Controlled Image Retrieval
arXiv
·
01 Jan 2023
·
doi:10.48550/arXiv.2307.07336
VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
arXiv
·
01 Jan 2023
·
doi:10.48550/arXiv.2305.12427
GaitFi: Robust Device-Free Human Identification via WiFi and Vision Multimodal Learning
IEEE Internet of Things Journal
·
01 Jan 2023
·
doi:10.1109/JIOT.2022.3203559
2022
Telesonar
Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems
·
06 Nov 2022
·
doi:10.1145/3560905.3568500
STUN: Self-Teaching Uncertainty Estimation for Place Recognition
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
23 Oct 2022
·
doi:10.1109/IROS47612.2022.9981546
OdomBeyondVision: An Indoor Multi-modal Multi-platform Odometry Dataset Beyond the Visible Spectrum
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
·
23 Oct 2022
·
doi:10.1109/IROS47612.2022.9981865
Pedestrian Liveness Detection Based on mmWave Radar and Camera Fusion
2022 19th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)
·
20 Sep 2022
·
doi:10.1109/SECON55815.2022.9918553
Cross Vision-RF Gait Re-identification with Low-cost RGB-D Cameras and mmWave Radars
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
·
06 Sep 2022
·
doi:10.1145/3550325
Self-Supervised Scene Flow Estimation With 4-D Automotive Radar
IEEE Robotics and Automation Letters
·
01 Jul 2022
·
doi:10.1109/LRA.2022.3187248
Graph-Based Thermal–Inertial SLAM With Probabilistic Neural Networks
IEEE Transactions on Robotics
·
01 Jun 2022
·
doi:10.1109/TRO.2021.3120036
DC-Loc: Accurate Automotive Radar Based Metric Localization with Explicit Doppler Compensation
2022 International Conference on Robotics and Automation (ICRA)
·
23 May 2022
·
doi:10.1109/ICRA46639.2022.9811561
AutoPlace: Robust Place Recognition with Single-chip Automotive Radar
2022 International Conference on Robotics and Automation (ICRA)
·
23 May 2022
·
doi:10.1109/ICRA46639.2022.9811869
Demo Abstract: 3D Simultaneous localization and Mapping with Power Network Electromagnetic Radiation
2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
·
01 May 2022
·
doi:10.1109/IPSN54338.2022.00046
2021
DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
IEEE Transactions on Neural Networks and Learning Systems
·
01 Dec 2021
·
doi:10.1109/TNNLS.2021.3112460
Motion Tracklet Oriented 6-DoF Inertial Tracking Using Commodity Smartphones
Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems
·
15 Nov 2021
·
doi:10.1145/3485730.3494116
Can Image Style Transfer Save Automotive Radar?
Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems
·
15 Nov 2021
·
doi:10.1145/3485730.3492888
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
·
01 Oct 2021
·
doi:10.1109/ICCV48922.2021.01570
3D Motion Capture of an Unmodified Drone with Single-chip Millimeter Wave Radar
2021 IEEE International Conference on Robotics and Automation (ICRA)
·
30 May 2021
·
doi:10.1109/ICRA48506.2021.9561738
Human tracking and identification through a millimeter wave radar
Ad Hoc Networks
·
01 May 2021
·
doi:10.1016/j.adhoc.2021.102475
Deep Neural Network Based Inertial Odometry Using Low-Cost Inertial Measurement Units
IEEE Transactions on Mobile Computing
·
01 Apr 2021
·
doi:10.1109/TMC.2019.2960780
2020
Indoor positioning system in visually-degraded environments with millimetre-wave radar and inertial sensors
Proceedings of the 18th Conference on Embedded Networked Sensor Systems
·
16 Nov 2020
·
doi:10.1145/3384419.3430421
milliEgo
Proceedings of the 18th Conference on Embedded Networked Sensor Systems
·
16 Nov 2020
·
doi:10.1145/3384419.3430776
See through smoke
Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services
·
15 Jun 2020
·
doi:10.1145/3386901.3388945
Heart Rate Sensing with a Robot Mounted mmWave Radar
2020 IEEE International Conference on Robotics and Automation (ICRA)
·
01 May 2020
·
doi:10.1109/ICRA40945.2020.9197437
Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference
IEEE Internet of Things Journal
·
01 May 2020
·
doi:10.1109/JIOT.2020.2966773
Nowhere to Hide: Cross-modal Identity Leakage between Biometrics and Devices
Proceedings of The Web Conference 2020
·
20 Apr 2020
·
doi:10.1145/3366423.3380108
AtLoc: Attention Guided Camera Localization
Proceedings of the AAAI Conference on Artificial Intelligence
·
03 Apr 2020
·
doi:10.1609/aaai.v34i06.6608
DeepTIO: A Deep Thermal-Inertial Odometry With Visual Hallucination
IEEE Robotics and Automation Letters
·
01 Apr 2020
·
doi:10.1109/LRA.2020.2969170
2019
Autonomous Learning of Speaker Identity and WiFi Geofence From Noisy Sensor Data
IEEE Internet of Things Journal
·
01 Oct 2019
·
doi:10.1109/JIOT.2019.2926645
iSCAN
Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers
·
09 Sep 2019
·
doi:10.1145/3341162.3344858
MotionTransformer: Transferring Neural Inertial Tracking between Domains
Proceedings of the AAAI Conference on Artificial Intelligence
·
17 Jul 2019
·
doi:10.1609/aaai.v33i01.33018009
Selective Sensor Fusion for Neural Visual-Inertial Odometry
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
·
01 Jun 2019
·
doi:10.1109/CVPR.2019.01079
Autonomous Learning for Face Recognition in the Wild via Ambient Wireless Cues
The World Wide Web Conference
·
13 May 2019
·
doi:10.1145/3308558.3313398
mID: Tracking and Identifying People with Millimeter Wave Radar
2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)
·
01 May 2019
·
doi:10.1109/DCOSS.2019.00028
Efficient Indoor Positioning with Visual Experiences via Lifelong Learning
IEEE Transactions on Mobile Computing
·
01 Apr 2019
·
doi:10.1109/TMC.2018.2852645
Semantic Place Understanding for Human–Robot Coexistence—Toward Intelligent Workplaces
IEEE Transactions on Human-Machine Systems
·
01 Apr 2019
·
doi:10.1109/THMS.2018.2875079
HydraDoctor
Proceedings of the 20th International Conference on Distributed Computing and Networking
·
04 Jan 2019
·
doi:10.1145/3288599.3288635
2018
Automatic Face Recognition Adaptation via Ambient Wireless Identifiers
Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems
·
04 Nov 2018
·
doi:10.1145/3274783.3275191
Simultaneous Localization and Mapping with Power Network Electromagnetic Field
Proceedings of the 24th Annual International Conference on Mobile Computing and Networking
·
15 Oct 2018
·
doi:10.1145/3241539.3241540
Deepauth
Proceedings of the 2018 ACM International Symposium on Wearable Computers
·
08 Oct 2018
·
doi:10.1145/3267242.3267252
CommonSense
Proceedings of the 1st International Workshop on Internet of People, Assistive Robots and Things
·
10 Jun 2018
·
doi:10.1145/3215525.3215526
Learning 3D Scene Semantics and Structure from a Single Depth Image
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
·
01 Jun 2018
·
doi:10.1109/CVPRW.2018.00069
IONet: Learning to Cure the Curse of Drift in Inertial Odometry
Proceedings of the AAAI Conference on Artificial Intelligence
·
26 Apr 2018
·
doi:10.1609/aaai.v32i1.12102
Snoopy
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
·
08 Jan 2018
·
doi:10.1145/3161196
2017
Towards Self-supervised Face Labeling via Cross-modality Association
Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems
·
06 Nov 2017
·
doi:10.1145/3131672.3136991
VeriNet
Proceedings of the First ACM Workshop on Mobile Crowdsensing Systems and Applications
·
06 Nov 2017
·
doi:10.1145/3139243.3139251
SCAN
Proceedings of the 16th ACM/IEEE International Conference on Information Processing in Sensor Networks
·
18 Apr 2017
·
doi:10.1145/3055031.3055073
Leveraging User Activities and Mobile Robots for Semantic Mapping and User Localization
Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction
·
06 Mar 2017
·
doi:10.1145/3029798.3038343
2016
Robust occupancy inference with commodity WiFi
2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob)
·
01 Oct 2016
·
doi:10.1109/WiMOB.2016.7763228
Standardizing location fingerprints across heterogeneous mobile devices for indoor localization
2016 IEEE Wireless Communications and Networking Conference
·
01 Apr 2016
·
doi:10.1109/WCNC.2016.7564800
BlueDetect: An iBeacon-Enabled Scheme for Accurate and Energy-Efficient Indoor-Outdoor Detection and Seamless Location-Based Service
Sensors
·
22 Feb 2016
·
doi:10.3390/s16020268
A Robust Indoor Positioning System Based on the Procrustes Analysis and Weighted Extreme Learning Machine
IEEE Transactions on Wireless Communications
·
01 Feb 2016
·
doi:10.1109/TWC.2015.2487963
Robust Extreme Learning Machine With its Application to Indoor Positioning
IEEE Transactions on Cybernetics
·
01 Jan 2016
·
doi:10.1109/TCYB.2015.2399420
2015
A mutual information based online access point selection strategy for WiFi indoor localization
2015 IEEE International Conference on Automation Science and Engineering (CASE)
·
01 Aug 2015
·
doi:10.1109/CoASE.2015.7294059
A Fast and Precise Indoor Localization Algorithm Based on an Online Sequential Extreme Learning Machine
Sensors
·
15 Jan 2015
·
doi:10.3390/s150101804
2014
Extreme learning machine with dead zone and its application to WiFi based indoor positioning
2014 13th International Conference on Control Automation Robotics & Vision (ICARCV)
·
01 Dec 2014
·
doi:10.1109/ICARCV.2014.7064376
Robust extreme learning machine for regression problems with its application to wifi based indoor positioning system
2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
·
01 Sep 2014
·
doi:10.1109/MLSP.2014.6958903
An online sequential extreme learning machine approach to WiFi based indoor positioning
2014 IEEE World Forum on Internet of Things (WF-IoT)
·
01 Mar 2014
·
doi:10.1109/WF-IoT.2014.6803130