Anukriti Singh

About Me

I am a Ph.D. student in Computer Science at the University of Maryland, College Park, advised by Prof. Pratap Tokekar in the RAAS Lab.

My research sits at the intersection of perception and robot learning, with a focus on building manipulation and navigation systems that generalize in the real world. I'm especially interested in learning from rich supervision—video, language, demonstrations, and preference feedback—and using foundation-scale vision models to make policies and rewards more data-efficient and robust.

Education

2025 – Present College Park, MD

Ph.D. in Computer Science University of Maryland

Advised by Prof. Pratap Tokekar in the RAAS Lab.
Focusing on robot learning, foundation models, and real-world generalizable manipulation.

Completed College Park, MD

Master of Engineering (Robotics) University of Maryland

Specialized in perception, mobile robot navigation, and reinforcement learning.

Professional Experience Connecting industry and academic roles

May 2026 – Sept 2026 Paris, France

Research Intern Enchanted Tools

Researched Signal Temporal Logic (STL) and Vision-Language Models (VLMs) to specify high-precision action generation.
Bridged natural language intent with robust robotic manipulation guarantees.

Signal Temporal Logic VLM Action Generation Mobile Manipulation

📄 Resulted in STeP paper (In Submission, arXiv 2026)

Jun 2024 – Dec 2024 College Park, MD

Faculty Research Assistant UMIACS, UMD

Developed a framework for bootstrapping reinforcement learning using 2D sketch trajectories.
Achieved 96% of teleop baseline performance and a 170% improvement over pure RL methods.

Reinforcement Learning Trajectory Sketching Robotic Manipulation

📄 Resulted in Sketch-to-Skill paper (RSS 2025)

Feb 2024 – May 2024 NJ / Remote

Robotics Co-op Nokia Bell Labs

Curated large-scale warehouse data for training robust segmentation models.
Adapted 3D multi-object tracking to 2D using Kalman filters, significantly reducing false positive rates.

Kalman Filtering 3D Multi-Object Tracking Warehouse Segmentation

Jun 2023 – Aug 2023 Murray Hill, NJ

Robotics Intern Nokia Bell Labs

Engineered a zero-shot 6D pose estimation pipeline by integrating YOLO, SfM, and PnP.
Optimized computational efficiency by 50%, enabling robust real-time tracking performance.

6D Pose Estimation Zero-Shot Learning YOLO & PnP

Mar 2022 – Aug 2022 Remote

Researcher PicsArt AI Research

Designed a novel vision-language architecture for zero-shot semantic segmentation.
Leveraged prompt-conditioned language tokens to significantly improve cross-modal alignment.

Zero-Shot Segmentation Transformers Vision-Language Alignment

📄 Resulted in SeMask paper (ICCV Workshop 2023)

Jul 2021 – Mar 2022 Hyderabad, India

Research Assistant RRC, IIIT Hyderabad

Conducted research in visual grounding and dense captioning.
Focused on creating precise mappings between semantic natural language tokens and 3D visual coordinates.

Visual Grounding Dense Captioning

Jan 2021 – Jun 2021 Bhopal, India

Research Assistant MOON Lab

Engineered recommendation systems to characterize complex quantum evolutions.
Applied collaborative filtering algorithms to domain-specific physics challenges.

Quantum Computing Collaborative Filtering

📄 Resulted in Quantum Evolutions paper (Quantum Journal 2021)

Feb 2020 – Oct 2020 Eugene, OR

Visiting Student SHI Lab, UO

Explored intersections of visual grounding and object detection.
Merged semantic localization models with dense object detectors for improved scene understanding.

Visual Grounding Object Detection