Prajval Vaskar

To collect the steering and velocity data for training

Performane considering uniform velocity

Region growing based on intensity difference and centroid distance

Balloon model and Rubber model are implemented

Pretrained weights of VGG16 are used

Ultrasonic sensors are used with Kalman Filtering

Canny edge lane detection and Lane keeping using Stanley Controller
and prediction using Deep Learning

Lidar data is used to find the error for PID implementation

The algorithm uses LIDAR data to determine gaps and chooses the gap with more space

Disparity Extender implemented on the f1/10th

Downsized MotoGP map used in the race

Docker containerization stucture used for head to head race

Used AprilTag detector package

Used OpenCV and centroid method for line recognition

Used 2D Point cloud data from Lidar to navigate

Used Finite State Machine for Behavior control

Local Navigation in Obstacle Space

Detecting and Tracking Yellow line's center

Used 2D Lidar data to navigate

Local Navigation avoiding static obstacles

Turtlebot basics- Controls

Turtlebot basics- Lidar use

Force-based Local Navigation under uncertainity

Local Navigation under uncertainity for crowd

Path Finding algorithms

Path Finding algorithms

Path Finding algorithms

Sampling Based path planning algorithm

Computes a full probability distribution over an agent's location

Approximates the same distribution using a set of samples