PROJECTS
01
Risk Aware Merging
In this work we present a motion planning framework for autonomous vehicles to perform merge manevers in dense traffic. Our framework is divided into a two layer structure, Lane selection and scale optimization layer. Our framework guarantees a collision-free velocities even in dense traffic scenarios.
02
Self-Driving Car: Mahindra Rise Challenge
This competition involves the development of a Driverless car for Indian traffic scenarios. My work in this project was majorly the development of localisation and Planner pipeline for the car. For this I have developed a sensor fusion node that integrates the IMU data with wheel odometry and visual odometry and the RTK GNSS system. I have also developed a gradient aware longitudinal speed controller coupled with a planner that does static obstacle avoidance.
03
Trajectory Planner for Autonomous Navigation
I have developed a real-time reactive planner for generating dynamically feasible paths to navigate through an environment that includes static obstacles
04
Road Segmentation with different Classifiers
In this work we developed different classification models for road segmentation. The classification models we used are Superpixel based Classification(SVM, Naive Bayes, KNN, Random Forests,), Neural Network Based Classification (CNN) . This is implemented KITTI Road Datasets.
05
Motion Planning under Non- Parametric Uncertainty through Embedding in RKHS
In this work, we developed an efficient algorithm for solving a class of chance constrained optimization by representing the non-parametric uncertainty as functions in Reproducing Kernel Hilbert Space( RKHS).
06
LOCALISATION & NAVIGATION IN GPS DENIED ENVIRONMENT
In this project we developed an algorithm that fuses the sensor data from a visual sensor and an IMU to estimate the robot's current location and navigate the robot to its destination with obstacle avoidance in GPS denied environment. Not having the GPS data makes the problems more challenging due to absence of fixed global reference frame. The real time implementation of these algorithms were tested on a Clearpath A200 robot.