CV
Curriculum vitae
Contact Information
| Name | Yash Turkar |
| Professional Title | Autonomy Intern at Skydio and Ph.D. student in Computer Science at the University at Buffalo |
| [email protected] | |
| Location | Buffalo, NY |
| Website | https://yash.turkar.in |
Professional Summary
My research centers on utility-aware robot perception: understanding how the quality of visual data shapes downstream performance, and how robots can act to acquire more informative measurements. I am particularly interested in the perception-action loop for field robots in challenging environments, with an emphasis on active sensing, low-light vision, and robust visual navigation under real-world sensing constraints.
Experience
-
2026 - Present Autonomy Intern
Skydio
Inspection and mapping team
- Developed and deployed learning-based perception algorithms for distribution pole detection and localization.
-
2022 - 2026 Buffalo, NY
Graduate Research Assistant
University at Buffalo
DRONES Lab
- Conducted research in perception and autonomy for field robots across VLM-based view planning, active low-light imaging, and mapping-quality metrics.
- Formulated hypotheses, designed controlled experiments and ablations, built reproducible evaluation pipelines, and validated results across simulation and field deployments.
-
2023 - 2023 Houston, TX
Intern, Autonomous Robotics
SLB
- Built a sensing-modality evaluation framework across LiDAR, RGB, and thermal sensing for autonomous inspection on quadrupeds.
- Produced data-driven sensor and configuration recommendations from field validation.
-
2022 - 2022 Houston, TX
Intern, Autonomous Robotics
SLB
- Benchmarked dense SLAM with mixed simulation and field datasets for onshore inspection.
- Improved robustness and inspection frequency in a quadruped proof-of-concept deployment.
-
2024 - 2024 Buffalo, NY
Instructor and Teaching Fellow, CSE 4/568 Robotics Algorithms
University at Buffalo
- Completely redesigned the syllabus and created ROS-based programming assignments for more than 50 students.
- Taught first-principles autonomy, including kinematics, probabilistic localization and mapping, planning, and navigation.
-
2022 - 2023 Buffalo, NY
Teaching Assistant, CSE 4/568 Robotics Algorithms
University at Buffalo
- Led weekly discussions, held office hours, and graded exams.
- Designed auto-graded assignments and maintained Piazza and the course GitHub.
Academic Interests
Education
-
2022 - Present PhD
University at Buffalo
Computer Science
-
2021 - 2023 Master's
University at Buffalo
Computer Science
-
2016 - 2020 Bachelor's
University of Mumbai
Computer Engineering
Publications
-
2025 Active Illumination Control in Low-Light Environments
International Symposium on Experimental Robotics (ISER) 2025
-
2026 QAL: A Loss for Recall-Precision Balance in 3D Reconstruction
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026
-
2026 Lightning: Adaptive Illumination Control for Robot Perception
Under submission and review
-
2025 TERA: A Simulation Environment for Terrain Excavation Robot Autonomy
IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR) 2025
-
2024 VRF: Vehicle Road-Side Point Cloud Fusion
ACM MobiSys 2024
-
2026 Learning Visual Information Utility with PIXER
Conference on Robots and Vision (CRV) 2026, accepted
-
2023 Kinematics-only Differential Flatness Based Trajectory Tracking for Autonomous Racing
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023
-
2026 Empir3D: A Framework for Multi-Dimensional Point Cloud Assessment
Conference on Robots and Vision (CRV) 2026, accepted
Projects
-
Adaptive Illumination Control for Robot Perception
Closed-loop illumination control for robot perception that improves visual SLAM robustness in low-light and high-dynamic-range scenes.
- Introduced a relighting model to separate ambient illumination from light contribution and synthesize physically consistent multi-intensity training data.
- Distilled an offline optimal intensity schedule into a real-time controller that balances SLAM utility, power consumption, and temporal smoothness.
-
NightHawk: Active Illumination Control
Active illumination and exposure control for low-light robot perception.
- Used Bayesian optimization and a feature-utility metric to improve feature detection and matching in low light.
- Implemented the event-triggered optimization loop, camera and light control, and the Mfeat utility metric for field deployments.
-
INSPECTOR: Autonomous Culvert Inspection on the Erie Canal
Deployed autonomous culvert inspection system for Erie Canal missions using a legged robot.
- Integrated inspection sensing, navigation, and field-ready autonomy for culvert deployments on Spot.
- Built the data-collection and autonomy workflow for constrained, low-light culvert inspection runs.
-
VISION
Under-submission language-in-the-loop inspection work that pairs open-vocabulary perception with viewpoint planning on a legged robot.
- Integrated VLM prompting, stereo-scale recovery, and culvert-aware planning on Spot.
- Designed a low-cost 3D-printed pan-tilt camera gimbal controllable through ROS 2.
-
PIXER: Learning Visual Information Utility
Lightweight model that predicts pixel-wise featureness and uncertainty to improve visual odometry with fewer features.
- Designed the Bayesian learning pipeline and evaluation, reducing visual odometry RMSE while using substantially fewer features.
-
Empir3D: Multi-Dimensional Point Cloud Quality Assessment
Four-axis point-cloud quality framework spanning resolution, accuracy, coverage, and artifacts.
- Implemented metrics and analysis tools and ran SLAM and completion case studies beyond single-distance measures.
-
EARTH: Excavation Autonomy with Resilient Traversability and Handling
Excavation autonomy framework integrating perception, planning, hydraulic control, and the TERA simulator.
- Led perception and simulation components and integrated safe control and state-estimation modules.
-
Hex-Wife: Hex-rotor UAV Platform
Low-cost hex-rotor UAV platform built for AUVSI SUAS 2019 autonomous flight tests and payload experiments.
- Covered airframe and avionics design, flight-stack and state-estimation integration, controller tuning, and field validation.
Skills
Reviewing
- IEEE International Conference on Robotics and Automation (ICRA), reviewer (2024-present)
- IEEE International Conference on Intelligent Robots and Systems (IROS), reviewer (2025-present)
- IEEE Robotics and Automation Letters (RA-L), reviewer (2024-present)
Honors and Awards
-
2022 CSE Graduate Leadership Award
University at Buffalo
-
2019 Just Joe Sportsmanship Award
AUVSI SUAS