Planning through Collision-Free Ellipsoidal Corridors With Orthogonal Trust Region Problems
Jaitly, A. Arrizabalaga, J. Li, G (Submitted to ICRA 26)
Building reliable motion for real-world robots
Hi, I’m Akshay Jaitly — a robotics researcher focused on motion planning, control, and safe autonomy. I develop new classes of optimization solvers that exploit problem structure and rigorous geometric representations of complex mathematical problems, with applications to robotics and autonomous systems.
Publications
Papers and ResearchAnalytic Conditions for Differentiable Collision Detection in Trajectory Optimization
Jaitly, A. Jha, K D. Ota, K. Shirai, Y. (IROS 25)
PAAMP: Polytopic Action-Set and Motion Planning for Long Horizon Dynamic Motion Planning via Mixed Integer Linear Programming
Jaitly, A. Farzan, S. (IROS 24)
Galileo: An Efficient Pseudospectral Collocation Framework for Legged Robots
Chandler, E. Jaitly, A. Agheli, M. (ICRA @40)
A MILP-Based Framework for Coordinated Multi-Agent Motion Planning and Collision Avoidance in Constrained Environments
Farzan, S. Jaitly, A. Cline J. (CASE 25)
Featured Projects
A few things I’ve built
MILP
IROS 2024
Polytopic Action & Motion Planning (PAAMP)
Linearizing long-horizon dynamic motion planning with learned polytopes.
C++
Galileo
Multi-Contact Planning on Unitree Go1
Perceptive locomotion: walking, hopping, trotting with switched-system collocation.
C++
Arduino
LLAMA-Q: A C++ Library to Abstract and Generalize Robot Control
MIT THINK award finalist; granted a presentation slot at MakerFaire 2020.
MATLAB
Degen_vert2lcon: A MATLAB library to find the Convex Hull of points that lie in an affine subspace
Published on MATLAB file exchange, this addressed limitations of existing methods for finding convex hulls.
ROS
Trajectory
Trajectory Tracking for Quadrotor
Robust Trajectory Tracking for Quadrotor using Sliding Mode Control.
Trajectory
Single Level Contact Aware TrajOpt
Single Level Contact Aware TrajOpt (Done with MERL, under NDA).
Swarm Communication
Distributed Task Allocation for Communication in Intermittent Swarms
Solving a distributed optimization with analytic bounds on communication frequency.
Sky-Cam
Cable-driven
Wirebot Platform -- A < $50 platform for speedy locomotion in large indoor spaces.
Kinematics
Trajectory
Hephaestus Arm Control
Implementing and using Vision, Position/Velocity Kinematics, Trajectory Planning, Communication to enable robot control.
Experience
Where I’ve learned
Aerial Control and Perception Lab. WPI - Visiting Researcher
March 2025 - Present • Worcester, MA
● Leading to submissions in ICRA & IJRR.
● Created a new, speedy, solver for the Trust Region Problem with proof of convergence.
●Introduced a new, “Orthogonal Trust Regions Problem” (Orth-TRP) with similar, exploitable, structure. The OrthTRP is directly applicable to training neural networks, performing contact-implicit optimization, etc. We utilize it for collision avoidant trajectory optimization (in drones) in our current work.
● Created new parameterizations of free space, allowing trajectory optimization to be solved as an Orth-TRP, faster than established methods.
● Created a new, speedy, solver for the Trust Region Problem with proof of convergence.
●
● Created new parameterizations of free space, allowing trajectory optimization to be solved as an Orth-TRP, faster than established methods.
Mitsubishi Electric Research Labs (MERL) - Optimization and Intelligent Robotics (Under NDA) — Research Intern
June 2024 - March 2025 • Cambridge, MA
● Single Level Collision detection For Trajectory Optimization
- Outperformed other state-of-the-art methods like DCOL (Tracy et all).
- Led to a publication in IROS ‘25 and a patent. See “Publications” for specific contributions.
● Learning Traffic for Elevator Scheduling
- Learning based Multi-variate time-series prediction with improved synthetic data generation.
- Dynamic-programming based algorithm to perform optimal job scheduling.
- Outperformed other state-of-the-art methods like DCOL (Tracy et all).
- Led to a publication in IROS ‘25 and a patent. See “Publications” for specific contributions.
● Learning Traffic for Elevator Scheduling
- Learning based Multi-variate time-series prediction with improved synthetic data generation.
- Dynamic-programming based algorithm to perform optimal job scheduling.
Boston Dynamics - Spot Manipulation Software Engineering Intern
May 2023 - August 2023 • Waltham, MA
● Contributed services for Gripper Cameras incorporated in the Spot 4.0 software release.
● Worked with image processing & legged control techniques to enhance camera calibration.
● Worked with image processing & legged control techniques to enhance camera calibration.
Autonomous Loco-Manipulation Systems Group. WPI - Research
August 2023 - May 2024 • Worcester, MA
● Worked on Galileo (see “Publications”), a software library enabling pseudo-spectral optimization for legged robot motion planning.
● This work (>60 stars) was used in other projects, including HURON (humanoid robots) and BiQu (quadrupedal robot loco-manipulation).
● This work (>60 stars) was used in other projects, including HURON (humanoid robots) and BiQu (quadrupedal robot loco-manipulation).
About
I’m a robotics engineer who enjoys turning messy real-world constraints into reliable motion. My toolkit includes C++, Python, Drake, PyTorch, ROS 2, Matlab, CasADI, Git, OpenCV, Eigen. I like practical systems with tight feedback loops and clear metrics.
Interests: Optimization, Algebraic Geometry, Motion Planning, Switched Systems, Underactuated Control.