Siddharth Ancha
email@h.sadumcetain unscramble

| CV | Google Scholar | Github |

I am a research scientist at MIT, working with Leslie Kaelbling, Tomás Lozano-Pérez and Nicholas Roy. My current research interests are in combining learning-based and model-based methods for robotic manipulation. Towards this goal, I draw on techniques at the intersection of machine learning, computer vision, motion planning and optimization.

I obtained my PhD in the Machine Learning Department at CMU, co-advised by David Held and Srinivasa Narasimhan. My PhD work developed active perception algorithms for Programmable Light Curtains, a fast and high-resolution depth sensor that needs to be controlled intelligently in order to sense efficiently.

Prior to that, I was a masters student in the Department of Computer Science at the University of Toronto, where I worked on statistical machine learning with Daniel Roy and Roger Grosse. I also spent multiple summers working with Aditya Nori at Microsoft Research Cambridge. I graduated from IIT Guwahati with a major in Computer Science and a minor in Mathematics.


  News
Jan '25 NEW! Our paper on anomaly detection using diffusion models for off-road navigation is accepted to ICRA 2025!
Jun '24 Our paper on learning traversability for risk-aware navigation is accepted to the Transactions in Robotics (T-RO) 2024!
May '24 Our paper on learning traversability priors using diffusion models for path planning is accepted to the ICRA 2024 Workshop on Resilient Off-road Autonomy as an Oral presentation!
Apr '24 🏆 Our paper on uncertainty estimation for semantic segmentation is nominated for the best paper award in the robot vision category at ICRA 2024!
Apr '23 Our paper on velocity estimation using light curtains is accepted to RSS 2023!
Apr '23 🏆 Selected to Rising Stars in Cyber-Physical Systems at the University of Virginia in May 2023!
Sep '22 🏆 Honored to receive the IROS 2022 Outstanding Reviewer Award, awarded to 5 out of 4,291 reviewers!
Jul '22 Successfully defended my PhD thesis! A big thanks to my thesis committee: David Held, Srinivasa Narasimhan, Katerina Fragkiadaki and Wolfram Burgard. Also thanks to Chris Atkeson for the many insightful and interesting questions!
Feb '22 Excited to join Nick Roy's Robust Robotics Group at MIT as a postdoc this August!
Dec '21 Proposed my PhD thesis titled Active robot perception using programmable light curtains. Expected to defend and graduate in July 2022. Thesis committee: David Held, Srinivasa Narasimhan, Katerina Fragkiadaki and Wolfram Burgard.
Nov '21 Published a CMU ML Blog Post on our recent work on safety envelopes using light curtains, presented at RSS '21. Check it out!

  Education
image not found Massachusetts Institute of Technology
Postdoctoral Associate
Computer Science & Artificial Intelligence Lab (CSAIL)
2022 ─ Present
image not found Carnegie Mellon University
PhD, Machine Learning Department
School of Computer Science (SCS)
2017 ─ 2022
image not found University of Toronto
MS in Computer Science
Department of Computer Science (DCS)
2015 ─ 2017
image not found Indian Institute of Technology, Guwahati
BTech Major in Computer Science & Engineering
BTech Minor in Mathematics
2011 ─ 2015


  Publications
image not found

Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation
Siddharth Ancha*, Sunshine Jiang*, Travis Manderson, Laura Brandt, Yilun Du, Philip R. Osteen, Nicholas Roy
ICRA 2025

webpage | abstract | pdf | bibtex | talk | code | colab

@inproceedings{jiang2025icra,
  title     = {Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigation},
  author    = {Sunshine Jiang AND Siddharth Ancha AND Travis Manderson AND Laura Brandt AND Yilun Du AND Philip R. Osteen AND Nicholas Roy}, 
  booktitle = {IEEE International Conference on Robotics and Automation (ICRA)}, 
  year      = {2025}, 
  address   = {Atlanta, USA}, 
  month     = {May}, 
}
image not found

Learning semantic traversability priors using diffusion models for uncertainty-aware global path planning
Ethan Fahnestock, Erick Fuentes, Philip R. Osteen, Siddharth Ancha, Nicholas Roy
ICRA'24 Workshop on Resilient Off-road Autonomy (Oral)

abstract | pdf | bibtex

  @inproceedings{fahnestock2024traversability,
    title     = {Learning semantic traversability priors using diffusion models for uncertainty-aware global path planning},
    author    = {Ethan Fahnestock AND Erick Fuentes AND Philip R. Osteen AND Siddharth Ancha AND Nicholas Roy}, 
    booktitle = {ICRA Workshop on Resilient Off-road Autonomy}, 
    year      = {2024},
  }
image not found

EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomy
Xiaoyi Cai, Siddharth Ancha, Lakshay Sharma, Philip R. Osteen, Bernadette Bucher, Stephen Phillips, Jiuguang Wang, Michael Everett, Nicholas Roy, Jonathan P. How
T-RO 2024

webpage | abstract | pdf | bibtex | talk

  @inproceedings{cai2023evora,
    title     = {EVORA: Deep EVidential Traversability Learning for Risk-Aware Off-Road Autonomy},
    author    = {Xiaoyi Cai AND Siddharth Ancha AND Lakshay Sharma AND Philip R. Osteen AND Bernadette Bucher AND Stephen Phillips AND Jiuguang Wang AND Michael Everett AND Nicholas Roy AND Jonathan P. How}, 
    booktitle = {arXiv preprint arXiv:2311.06234}, 
    year      = {2023},
  }
image not found

Deep Evidential Uncertainty Estimation for Semantic Segmentation under OOD Obstacles
Siddharth Ancha, Philip R. Osteen, Nicholas Roy
ICRA 2024 (Best paper nomination in robot vision)

webpage | abstract | pdf | bibtex | talk

  @inproceedings{ancha2024icra,
    title     = {Deep Evidential Uncertainty Estimation for Semantic Segmentation under Out-Of-Distribution Obstacles},
    author    = {Siddharth Ancha AND Philip R. Osteen AND Nicholas Roy}, 
    booktitle = {IEEE International Conference on Robotics and Automation (ICRA)}, 
    year      = {2024}, 
    address   = {Yokohama, Japan}, 
    month     = {May}, 
  }
image not found

Active Velocity Estimation using Light Curtains via Self-Supervised Multi-Armed Bandits
Siddharth Ancha, Gaurav Pathak, Ji Zhang, Srinivasa Narasimhan,
David Held
RSS 2023 (Invited to Autonomous Robots special issue)

webpage | abstract | pdf | bibtex | code | short talk | long talk

@inproceedings{ancha2023rss,
  title     = {Active Velocity Estimation using Light Curtains via Self-Supervised Multi-Armed Bandits},
  author    = {Siddharth Ancha AND Gaurav Pathak AND Ji Zhang AND Srinivasa Narasimhan AND David Held}, 
  booktitle = {Proceedings of Robotics: Science and Systems}, 
  year      = {2023}, 
  address   = {Daegu, Republic of Korea}, 
  month     = {July}, 
}
image not found

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks
Jianren Wang, Haiming Gang, Siddharth Ancha, Yi-Ting Chen, David Held
3DV 2021

webpage | abstract | pdf | bibtex | code | short talk | long talk | slides

@inproceedings{jianren21sod-tgnn,
  author    = {Jianren Wang AND Haiming Gang AND Siddarth Ancha AND Yi-Ting Cheng AND David Held},
  title     = {Semi-supervised 3D Object Detection via Temporal Graph Neural Networks},
  booktitle = {3DV},
  year      = {2021}
}

Active Safety Envelopes using Light Curtains with Probabilistic Guarantees
Siddharth Ancha, Gaurav Pathak, Srinivasa Narasimhan,
David Held
RSS 2021

webpage | abstract | pdf | bibtex | code | talk | blog

@inproceedings{Ancha-RSS-21, 
  author    = {Siddharth Ancha AND Gaurav Pathak AND Srinivasa Narasimhan AND David Held}, 
  title     = {Active Safety Envelopes using Light Curtains with Probabilistic Guarantees}, 
  booktitle = {Proceedings of Robotics: Science and Systems}, 
  year      = {2021}, 
  address   = {Virtual}, 
  month     = {July}, 
  doi       = {10.15607/rss.2021.xvii.045} 
}
image not found

Exploiting & Refining Depth Distributions with Triangulation Light Curtains
Yaadhav Raaj, Siddharth Ancha, Robert Tamburo, David Held, Srinivasa Narasimhan
CVPR 2021

webpage | abstract | pdf | bibtex | code | talk

@inproceedings{cvpr2021raajexploiting,
  author    = {Yaadhav Raaj AND Siddharth Ancha AND Robert Tamburo AND David Held, Srinivasa Narasimhan},
  title     = {Exploiting and Refining Depth Distributions with Triangulation Light Curtains},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2021}
}
image not found

Active Perception using Light Curtains for Autonomous Driving
Siddharth Ancha, Yaadhav Raaj, Peiyun Hu, Srinivasa Narasimhan, David Held
ECCV 2020 (Spotlight presentation)

webpage | abstract | pdf | bibtex | code | short talk | long talk | slides

@inproceedings{ancha2020eccv,
  author    = {Ancha, Siddharth AND Raaj, Yaadhav AND Hu, Peiyun AND Narasimhan Srinivasa G. AND Held, David},
  editor    = {Vedaldi, Andrea AND Bischof, Horst AND Brox, Thomas AND Frahm, Jan-Michael},
  title     = {Active Perception Using Light Curtains for Autonomous Driving},
  booktitle = {Computer Vision -- ECCV 2020},
  year      = {2020},
  publisher = {Springer International Publishing},
  address   = {Cham},
  pages     = {751--766},
  isbn      = {978-3-030-58558-7}
}
image not found

Uncertainty-Aware Self-Supervised 3D Data Association
Jianren Wang, Siddharth Ancha, Yi-Ting Chen, David Held
IROS 2020

webpage | abstract | pdf | bibtex | talk | slides | code

@inproceedings{jianren20s3da,
  author    = {Wang, Jianren AND Ancha, Siddharth AND Chen, Yi-Ting AND Held, David},
  title     = {Uncertainty-aware Self-supervised 3D Data Association},
  booktitle = {IROS},
  year      = {2020}
}
image not found

Combining Deep Learning and Verification for Precise Object Instance Detection
Siddharth Ancha*, Junyu Nan*, David Held
CoRL 2019

webpage | abstract | pdf | bibtex | talk | code

@inproceedings{FlowVerify2019CoRL,
  author    = {Siddharth Ancha AND Junyu Nan AND David Held},
  editor    = {Leslie Pack Kaelbling AND Danica Kragic AND Komei Sugiura},
  title     = {Combining Deep Learning AND Verification for Precise Object Instance Detection},
  booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings},
  series    = {Proceedings of Machine Learning Research},
  volume    = {100},
  pages     = {122--141},
  year      = {2019},
  url       = {https://proceedings.mlr.press/v100/ancha20a.html},
  timestamp = {Mon, 25 May 2020 15:01:26 +0200},
  biburl    = {https://dblp.org/rec/conf/corl/AnchaNH19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}
  Older Work
image not found

Autofocus Layer for Semantic Segmentation
Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha, Jay Nanavati, Garrison Cottrell, Antonio Criminisi, Aditya Nori
MICCAI 2018 (Oral presentation)

abstract | pdf | bibtex | code

@inproceedings{qin2018autofocus,
  title        = {Autofocus layer for semantic segmentation},
  author       = {Qin, Yao AND Kamnitsas, Konstantinos AND Ancha, Siddharth AND Nanavati, Jay AND Cottrell, Garrison AND Criminisi, Antonio AND Nori, Aditya},
  booktitle    = {International conference on medical image computing and computer-assisted intervention (MICCAI)},
  pages        = {603--611},
  year         = {2018},
  organization = {Springer}
}
image not found

Lifted Auto-Context Forests for Brain Tumour Segmentation
Loïc Le Folgoc, Aditya V. Nori, Siddharth Ancha, Antonio Criminisi
MICCAI 2016 BraTS Challenge (Winner)

abstract | pdf | bibtex

@inproceedings{le2016lifted,
  title       = {Lifted auto-context forests for brain tumour segmentation},
  author      = {Le Folgoc, Loic AND Nori, Aditya V AND Ancha, Siddharth AND Criminisi, Antonio},
  booktitle   = {International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries},
  pages       = {171--183},
  year        = {2016},
  organization= {Springer}
}
image not found

Measuring the reliability of MCMC inference with bidirectional Monte Carlo
Roger B. Grosse, Siddharth Ancha, Daniel M. Roy
NeurIPS 2016

abstract | pdf | bibtex | code

@inproceedings{NIPS2016_0e9fa1f3,
  author    = {Grosse, Roger B AND Ancha, Siddharth AND Roy, Daniel M},
  booktitle = {Advances in Neural Information Processing Systems},
  editor    = {D. Lee AND M. Sugiyama AND U. Luxburg AND I. Guyon AND R. Garnett},
  publisher = {Curran Associates, Inc.},
  title     = {Measuring the reliability of MCMC inference with bidirectional Monte Carlo},
  url       = {https://proceedings.neurips.cc/paper/2016/file/0e9fa1f3e9e66792401a6972d477dcc3-Paper.pdf},
  volume    = {29},
  year      = {2016}
}

  Conference Reviewing
2024 Robotics: Science and Systems (RSS), 2024
2024 Int. Conf. on Robotics & Automation (ICRA), 2024
2022 Conf. on Intelligent Robots & Systems (IROS), 2022

🏆 (Outstanding reviewer award: 5 / 4291 reviewers)

2021 NeurIPS Workshop on Ecological Theory of RL, 2021
2021 Conference on Robot Learning (CoRL), 2021
2020 Robotics: Science and Systems (RSS), 2020
2020 Conference on Robot Learning (CoRL), 2020
2019 NeurIPS Black in AI Workshop, 2019
2019 Robotics: Science and Systems (RSS), 2019
2019 Conference on Robot Learning (CoRL), 2019
2018 NeurIPS Black in AI Workshop, 2018

  Contact

Computer Science & Artificial Intelligence Laboratory
Stata Center, 32 Vassar St.
Massachusetts Institute of Technology
Cambridge, MA 02139


Template modified from this