Vrushabh Zinage's Projects
BarrierNet: differentiable Control Barrier Functions for Learning of Safe Robot Control
Massively parallel rigidbody physics simulation on accelerator hardware.
"Safety-Critical Control using Optimal-decay Control Barrier Functions with Guaranteed Point-wise Feasibility" by J. Zeng, B. Zhang, Z. Li and K. Sreenath https://arxiv.org/pdf/2103.12375.pdf
Matlab codes for safety-critical control based on a single CBF constructed from a complex combination of safety specifications. They contain codes for numerical simulation of three reach-avoid problems with a single obstacle, multiple obstacles and a road network.
A Large Quadcopter Swarm
๐Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
PyTorch Official Implementation of CoRL 2023 Paper: Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control
A General-Purpose Trajectory Optimizer for Multicopters
An efficient implementation of the Generalised Shape Expansion (GSE) Algorithm using OMPL
The official repo for NeurIPS 2021 paper 'Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks'
Material for the hands-on tutorial on Graph Deep Learning held at the Alan Turing Institute
Disturbance Observer-based Robust Integral Control Barrier Functions for Nonlinear Systems with High Relative Degree
Imitation Based Controller for MPC
Koopman Kernels for Learning Dynamical Systems from Trajectory Data
A collection of files that I use for augmenting the LaTeX editing experience with custom commands, environments, etc.
Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)
Model Predictive Control with discrete-time Control Barrier Functions (MPC-CBF).
The Multi Agent Motion Planning with Deadlock Resolution repository is a comprehensive collection of algorithms and methodologies aimed at addressing the critical challenge of deadlock avoidance in multi-agent social navigation scenarios.
Python implementation of a bunch of multi-robot path-planning algorithms.
A trajectory planning framework for multiple robots: paper accepted in IEEE T-RO
Code for the Nerf Navigation Paper. Implements a trajectory optimiser and state estimator which use NeRFs as an environment representation
Neural Koopman Lyapunov Control
The Open Motion Planning Library (OMPL)
Optimal Motion Generation-tools: motion planning made easy
Common used path planning algorithms with animations.
Demonstration of the PIPG algorithm for trajectory optimization
RO47005 Planning & Decision Making. Quadrotor model planner using probabilistic roadmap (PRM) and collision avoidance using Velocity Obstacles