INSOFE’s Autonomous Navigation course focuses on several algorithms related to mapping and motion planning for autonomous vehicles.
Navigate your CAReer in the autonomous world with this free course on algorithms for self-driving cars.
This course is designed for learners who are at the early to mid-stage of their careers, with the vision of self-driving cars around them and want to be a part of that journey.
It is ideal for engineers with a programming background with an inclination towards mathematics and simulations.
It is for people who want to use their creative thinking and technology acumen to build mobility for tomorrow.
- Classes are conducted live & online, every Monday from 6:30 PM to 7:30 PM IST, starting from November 23, 2020.
- There will be 10 classes in total and are repeated circularly. So, after the 10th class, the first class starts again.
- Every class is associated with an online quiz of 5 questions.
- The modules are made as independent as possible. So that students can join at several points and then complete 10 lectures. Typically, a student can start with the beginning of any module.
Live Hours: 1 hour per week
Additional hours to be spent: 3-5 hours per session
Do I get a badge: Yes. There is an evaluation and a badge.
Autonomous navigation is a key aspect of self-driving cars and it can be broadly divided into 4 stages. This 10-hour course provides an overview of techniques and algorithms related to 4 stages.
Ability of the system to 'see' through a camera and then process the data through computer vision algorithms.
Mapping & Localization
Localize the robot in the environment. (This may also include mapping or Simultaneous Localization and Mapping).
Path planning based on the available map.
Controlling the system to achieve the desired map.
Introduction to autonomous systems, stages in autonomous navigation, an overview of tools and algorithm
Computer vision: Point cloud
Computer vision: Lane and pedestrian detection
Sensor Fusion: Kalman Filter
Localization: Markov Localization & Particle FIlter
SLAM, EKF SLAM
Path Planning 1 A*, Dijkstra
Path Planning 2 RRT and DWA
Control, Reinforcement learning
ROS, GAzebo, RVIZ
Dr. Parag Mantri
Principal Data Scientist & Associate Professor
- Ph.D. in Aerospace Engineering from North Carolina State University, USA
- M.S. in Mechanical Engineering from Tufts University, USA
- B.E. in Mechanical Engineering from Osmania University Hyderabad, India
With over 12 years of experience in Engineering and R&D working in a wide spectrum of domains such as Aerospace, Oil & Gas, and Locomotive, he is a versatile engineer, researcher, and innovator. He has 7 filed patents (2 granted). Before joining INSOFE, he was Lead Research Engineer at GE Global Research.
He has also been an educator in a university set up as well as volunteering for community teaching for underprivileged children.
Dr. Mantri’s current focus is on Robotics, Autonomous Systems, and Connected Devices. He also works on applications of Machine Learning & Deep Learning in these areas.
He is responsible for developing interactive lab sessions and hackathons with real-world industry-specific problems cutting across several domains. His efforts focus on enhanced hands-on learning and career development of INSOFE students.