Lyft Perception Challenge
Achieve pixel-wise identification of objects in camera images. It was hosted by Udacity and Lyft’s Level 5 Engineering Center. details https://www.udacity.com/lyft-challenge
posts
2018
Home Service Robot
Program a home service robot that can autonomously map an environment and navigate to pickup and deliver objects.
IIWA Kinematics
Given a list of end-effector poses, calculate joint angles using Inverse Kinematics for the KUKA LBR IIWA R820
Lane Detection
Build a pipeline using distortion correction, image rectification, color transforms, and gradient thresholding to identify lane lines and their curvature.
2017
Behavioral cloning
Train a deep neural network to drive a car on winding road autonoumosly.
Perception Pick & Place
Given a cluttered tabletop scenario, perform object segmentation on 3D point cloud data using python-pcl to leverage the power of the Point Cloud Library, then identify target objects from a “Pick-List” in a particular order, pick up those objects and place them in corresponding drop boxes.