Charuvahan Adhivarahan
Multimodal Perception for Embodied Intelligence
Table of Contents
Charuvahan Adhivarahan
University at Buffalo, SUNY
Multimodal Perception & World Models for Autonomous Robots
Robots operating beyond controlled environments need representations that stay useful when sensor suites, physical surroundings, and embodiments change. My research builds multimodal representations and compact world models that integrate vision, depth, and non-visible spectra in real time, sustaining autonomy in unconstrained deployments.
Core Research Thrusts
Adaptive Representations for Embodied Intelligence
Robots need to preserve the details that matter for action within limited compute, latency, and bandwidth budgets. I develop adaptive, multi-resolution spatial representations and Lagrangian neural fields that concentrate detail where the task requires it. GoLF (Graphs over Lagrangian Fields) grounds this work in structured representations for robot planning, with the goal of making perception responsive to both the environment and the robot’s resources.
Adaptive & Active Mapping in Physical Worlds
A robot’s path determines what it can learn about its surroundings. I develop active perception methods that use uncertainty to choose informative viewpoints and trajectories for mapping physical phenomena. This work spans vegetation monitoring with VISTA and mapping invisible 3D airflow fields with Anemoi (ACM MobiCom ’23). The aim is to build accurate maps with fewer, carefully chosen observations.
Hierarchical World Model Abstractions
How can a robot use what it has learned when its environment, sensors, or physical capabilities change? My future research will connect structured spatial representations such as GoLF with generative world models through hierarchical abstractions. I aim to link multimodal observations to higher-level reasoning, so robots can predict how their surroundings evolve, adapt from simulation to the physical world, and transfer knowledge across different robot embodiments.
Publications
CLEAR: A Semantic–Geometric Terrain Abstraction for Large-Scale Unstructured Environments
IEEE RA-L 2026@article{meshram2026clear,
author = {Meshram, Pranay and Adhivarahan, Charuvahan and Esfahani, Ehsan Tarkesh and Chowdhury, Souma and Wang, Chen and Dantu, Karthik},
title = {{CLEAR}: A Semantic--Geometric Terrain Abstraction for Large-Scale Unstructured Environments},
journal = {IEEE Robotics and Automation Letters},
volume = {11},
number = {10},
pages = {11394--11401},
year = {2026},
doi = {10.1109/lra.2026.3726338},
url = {https://doi.org/10.1109/lra.2026.3726338}
}
TIPS: Thermal Image based Plastics Sorting
MobiSys 2026@inproceedings{duong2026tips,
author = {Duong, Long and Adhivarahan, Charuvahan and Ayyalasomayajula, Roshan and Dantu, Karthik},
title = {{TIPS}: Thermal Image based Plastics Sorting},
booktitle = {Proceedings of the ACM International Conference on Mobile Systems, Applications, and Services (MobiSys)},
pages = {247--260},
year = {2026},
publisher = {ACM},
doi = {10.1145/3745756.3809202},
url = {https://doi.org/10.1145/3745756.3809202}
}
Determining the percentage of recycled plastic content in a plastic product
Communications Engineering 2026@article{zhao2026determining,
author = {Zhao, Yaoli and Adhivarahan, Charuvahan and Jyothula, Chandra Lekha and Dantu, Karthik and Thundat, Thomas and Goyal, Amit},
title = {Determining the percentage of recycled plastic content in a plastic product},
journal = {Communications Engineering},
volume = {5},
number = {1},
eid = {51},
year = {2026},
doi = {10.1038/s44172-026-00639-y},
url = {https://doi.org/10.1038/s44172-026-00639-y}
}
QAL: A Loss for Recall–Precision Balance in 3D Reconstruction
WACV 2026@inproceedings{meshram2026qal,
author = {Meshram, Pranay and Turkar, Yash and Singh, Kartikeya and Masilamani, Praveen Raj and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {{QAL}: A Loss for Recall--Precision Balance in {3D} Reconstruction},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
pages = {7965--7974},
year = {2026},
publisher = {IEEE},
doi = {10.1109/wacv61042.2026.00769},
url = {https://doi.org/10.1109/wacv61042.2026.00769}
}
Anemoi: A Low-cost Sensorless Indoor Drone System for Automatic Mapping of 3D Airflow Fields
MobiCom 2023@inproceedings{xia2023anemoi,
author = {Xia, Stephen and Zhao, Minghui and Adhivarahan, Charuvahan and Hou, Kaiyuan and Chen, Yuyang and Nie, Jingping and Wu, Eugene and Dantu, Karthik and Jiang, Xiaofan},
title = {{Anemoi}: A Low-cost Sensorless Indoor Drone System for Automatic Mapping of {3D} Airflow Fields},
booktitle = {Proceedings of the ACM International Conference on Mobile Computing and Networking (MobiCom)},
pages = {77:1--77:16},
year = {2023},
publisher = {ACM},
doi = {10.1145/3570361.3613292},
url = {https://doi.org/10.1145/3570361.3613292}
}
Adaptive fovea for scanning depth sensors
IJRR 2020@article{tasneem2020adaptive,
author = {Tasneem, Zaid and Adhivarahan, Charuvahan and Wang, Dingkang and Xie, Huikai and Dantu, Karthik and Koppal, Sanjeev J},
title = {Adaptive fovea for scanning depth sensors},
journal = {The International Journal of Robotics Research},
volume = {39},
number = {7},
pages = {837--855},
year = {2020},
doi = {10.1177/0278364920920931},
url = {https://doi.org/10.1177/0278364920920931}
}
WISDOM: WIreless Sensing-assisted Distributed Online Mapping
ICRA 2019@inproceedings{adhivarahan2019wisdom,
author = {Adhivarahan, Charuvahan and Dantu, Karthik},
title = {{WISDOM}: {WIreless} Sensing-assisted Distributed Online Mapping},
booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
pages = {8026--8033},
year = {2019},
publisher = {IEEE},
doi = {10.1109/icra.2019.8793932},
url = {https://doi.org/10.1109/icra.2019.8793932}
}
Augmenting visual SLAM with Wi-Fi sensing for indoor applications
Autonomous Robots 2019@article{hashemifar2019augmenting,
author = {Hashemifar, Zakieh S. and Adhivarahan, Charuvahan and Balakrishnan, Anand and Dantu, Karthik},
title = {Augmenting visual {SLAM} with {Wi-Fi} sensing for indoor applications},
journal = {Autonomous Robots},
volume = {43},
number = {8},
pages = {2245--2260},
year = {2019},
doi = {10.1007/s10514-019-09874-z},
url = {https://doi.org/10.1007/s10514-019-09874-z}
}
Improving RGB-D SLAM using Wi-Fi: poster abstract
IPSN 2017@inproceedings{adhivarahan2017improving,
author = {Hashemifar, Zakieh Sadat and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {Improving {RGB-D} {SLAM} using {Wi-Fi}: poster abstract},
booktitle = {Proceedings of the ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)},
pages = {317--318},
year = {2017},
publisher = {ACM},
doi = {10.1145/3055031.3055067},
url = {https://doi.org/10.1145/3055031.3055067}
}
CLIPS: Continual Learning Infrastructure for Plastics Sorting
ICMLA 2025@inproceedings{mehta2025clips,
author = {Mehta, Shivm and Maheshkar, Vaishali and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {{CLIPS}: Continual Learning Infrastructure for Plastics Sorting},
booktitle = {Proceedings of the International Conference on Machine Learning and Applications (ICMLA)},
pages = {1197--1204},
year = {2025},
publisher = {IEEE},
doi = {10.1109/icmla66185.2025.00183},
url = {https://doi.org/10.1109/icmla66185.2025.00183}
}
A View-Planning Approach to 3D Reconstruction
XR Salento 2024@inproceedings{turkar2024view,
author = {Turkar, Yash and Aluckal, Christo and Adhivarahan, Charuvahan and Sebastiani, Alessandro and Dantu, Karthik},
title = {A View-Planning Approach to {3D} Reconstruction},
booktitle = {Extended Reality (XR Salento)},
series = {Lecture Notes in Computer Science},
volume = {15029},
pages = {340--350},
year = {2024},
publisher = {Springer Nature Switzerland},
doi = {10.1007/978-3-031-71710-9_27},
url = {https://doi.org/10.1007/978-3-031-71710-9_27}
}
Enhancing Archaeological Surveys with InSAR Imagery and UAV-Based GPR
IGARSS 2024@inproceedings{turkar2024enhancing,
author = {Turkar, Yash and De, Shaunak and Adhivarahan, Charuvahan and Mottola, Luca and Sebastiani, Alessandro and Castelletti, Davide and Dantu, Karthik},
title = {Enhancing Archaeological Surveys with {InSAR} Imagery and {UAV}-Based {GPR}},
booktitle = {Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},
pages = {11454--11456},
year = {2024},
publisher = {IEEE},
doi = {10.1109/igarss53475.2024.10640645},
url = {https://doi.org/10.1109/igarss53475.2024.10640645}
}
PANOS: Payload-Aware Navigation in Offroad Scenarios
arXiv 2024@misc{singh2024panos,
author = {Singh, Kartikeya and Turkar, Yash and Aluckal, Christo and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {{PANOS}: Payload-Aware Navigation in Offroad Scenarios},
year = {2024},
doi = {10.48550/arXiv.2409.16566},
url = {https://arxiv.org/abs/2409.16566},
eprint = {2409.16566},
archiveprefix = {arXiv},
primaryclass = {cs.RO}
}
Empir3D: A Framework for Multi-Dimensional Point Cloud Assessment
CRV 2026@inproceedings{turkar2026empir3d,
author = {Turkar, Yash and Meshram, Pranay and Aluckal, Christo and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {{Empir3D}: A Framework for Multi-Dimensional Point Cloud Assessment},
booktitle = {Proceedings of the Conference on Robots and Vision (CRV)},
year = {2026},
publisher = {PubPub},
doi = {10.21428/d82e957c.900da59a},
url = {https://doi.org/10.21428/d82e957c.900da59a},
eprint = {2306.03660},
archiveprefix = {arXiv},
primaryclass = {cs.CV}
}
Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting
arXiv 2025@misc{maheshkar2025detailed,
author = {Maheshkar, Vaishali and Ramakrishnan, Aadarsh Anantha and Adhivarahan, Charuvahan and Dantu, Karthik},
title = {Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting},
year = {2025},
doi = {10.48550/arXiv.2505.16513},
url = {https://arxiv.org/abs/2505.16513},
eprint = {2505.16513},
archiveprefix = {arXiv},
primaryclass = {cs.CV},
note = {Accepted at the 2024 REMADE Circular Economy Tech Summit and Conference}
}
Education
Academic Experience
Leading research in multimodal representations and compact world models for Embodied Intelligence. Directing experimental pipelines, mentoring Ph.D. and undergraduate researchers, and establishing cross-institutional collaborations with NASA and UVA.
Conducted high-fidelity motion capture research and maintained laboratory robotic systems including the Baxter robot, Universal Robots (UR5/UR10) arms, Clearpath Husky UGV, and OptiTrack optical mocap systems. Trained cross-disciplinary users and consulted on experimental designs.
Conducted office hours, lab recitations, and grading for CSE 468/568: Introduction to Robotics Algorithms (kinematics, probabilistic localization, SLAM, motion planning) and CSE 487/587: Data Intensive Computing (MapReduce, statistical analysis in R/Python, Hadoop/Spark ecosystems).
Professional Experience
Engineered full-stack applications with database architecture, distributed backend services, and front-ends for web, mobile, and connected television platforms.
Contact Information
| Davis Hall 106 | charuvah@buffalo.edu |
| Department of Computer Science & Engineering | (716) 645-1580 |
| University at Buffalo, SUNY | Google Scholar |
| Buffalo, NY 14260 USA | GitHub • LinkedIn |
Computer Skills
- Frameworks & Robotics: ROS/ROS2, PyTorch, TensorFlow, OpenCV, Point Cloud Library (PCL), Gazebo
- Languages: Python, C, C++, Java, JavaScript, MATLAB, Shell Scripting, R
- Domains & Algorithms: Multimodal Perception, Neural Radiance Fields / Gaussian Splatting, Visual-Inertial-RF SLAM, Sensor Fusion, Embodied AI, Reinforcement Learning
- Environments: Linux/Ubuntu, macOS, Windows, Git, Docker, Embedded Systems