Hello! I am Sandeep Reddy, a software intern in the planning and controls team at Kodiak Robotics Inc., a driverless technology company.

I graduated from the University of Washington (UW), Seattle where I was part of the Robot Learning Lab, directed by Professor Byron Boots. As a Research Assistant, I’ve had the pleasure of working on the DARPA RACER program, conducting research on robot motion planning and controls for high-speed off-road level 4 autonomous vehicles. After graduation, I joined the Bosch Center for Artificial Intelligence, working on the precise navigation problem for Lunar Rover autonomous docking, which is prepared for a series of flight missions, in collaboration with NASA. Post internship, I joined as a visiting researcher at the Carnegie Mellon University Robotics Institute, working with Professor Andrea Bajcsy on safe human-robot interaction for autonomous driving. Broadly, my interests include planning algorithms, robot policy learning, safe human-robot interaction, and planning under uncertainty.

Before joining UW, my undergraduate years at NIT Warangal, India, culminated in my leadership of a multifaceted SAE BAJA off-road racing team, comprising 25 individuals spanning software, simulation, and hardware domains. I invite you to explore my work below.

Resume - Here

Projects - Here

You can contact me at sandeep240599[at]gmail[dot]com or LinkedIn

Work Experience


Visiting Researcher | Robotics Institute - Carnegie Mellon University, Pittsburgh, PA (Sep. 2023 - Jan.2024)

  • Worked on integrating human motion prediction models with reachability to maintain optimally conservative safety monitor (Backward Reachable Tube for active collision-avoidance) in interactive autonomous driving

Robotics AI Software Intern | NASA PFP - Bosch Research, Pittsburgh, PA (Mar. 2023 - Sep. 2023)

  • Formulated robot decision-making architecture under uncertainties for autonomous docking and achieved 100% success
  • Incorporated external uncertainty learning with expert demos’ data making EKF quickly adapt to the lunar environment

DARPA RACER Program | Robot Learning Lab - University of Washington

  • Research Assistant (Sep. 2022 - Mar. 2023)
    • Executed Cross-entropy and Inverse RL to auto-tune the planner’s cost function saving 5 hours of manual tuning
    • Developed feature debugger that quantitatively compares nominal planner decisions with expert demonstrations
    • Implemented parallel version for cross-track error in MPC-based local planning that is 115X faster than serial computation
  • Software Engineering Intern (Jun. 2022 – Sep. 2022)
    • Implemented and tested safety-critical motion planning algorithms for high-speed off-road level 4 autonomous vehicles

Research & Development, Graduate Trainee Engineer | Bajaj Auto Ltd., Pune, India (Jan. 2021 – Jul. 2021)

  • Designed and validated a technique to find the precise cabin volume of any closed automobile with an accuracy of 98%
  • Wrote an optimization algorithm to find the best HVAC design parameters and validated them on different cars resulting in 95% accuracy

Captain, Designer – SAE BAJA off-road racing team | NIT Warangal (Apr. 2017 - Feb. 2020)

  • Led a 25-member cross-functional off-road vehicle team including software, simulation, suspension, steering, and brakes
  • Developed graphical sim using IoT and Matlab’s ThingSpeak to obtain the running status of the vehicle with < 2 sec delay
  • Improved chassis design using grid-independent technique and achieved overall weight under 150kg maintaining min. fos of 1.8