Learn · NPTEL

Course12710400176 lectures

Perception Algorithms for Autonomous Systems

Prof. Anirban Roy · IIT Kanpur

Start with lecture 1 At NPTEL

About

This course will provide detailed introduction of Environment perception algorithm block chain for autonomous platforms such as, Drone/Unmanned aerial vehicles (UAVs), Autonomous driver assistance systems (ADAS), Unmanned ground vehicles (UGVs) etc. Autonomous platforms gather perception information of the environment through multiple sensors measurements such as, Radar (FMCW/Phased array/Pulse Doppler), EO/IRST, Multi-function Camera and Lidar (MFCL), ultrasonics etc. This course will encompass 3 major object/target information processing stages as part of entire perception algorithm modules - Data-association and Multi Object tracking, Multi Sensor data and information fusion and Target classification. The course will focus on fundamentals of various estimation techniques like Maximum likelihood, Maximum-a- posteriori and Kalman filtering and its application to target tracking and sensor fusion.

Prerequisites: Primarily for ME/Ph.D with Control system or Signal Processing related specialization. However, BE (4th year) in EE, ETC or Automobile and Aerospace Engineering can also opt it as open elective.

Lectures

Week 1

  1. Lecture 1 - Introduction to Autonomous Systems YouTube
  2. Lecture 02 : Introduction to Autonomous Systems (Military Use Cases) YouTube
  3. Lecture 03: Review of Estimation Paradigms : The Least Square Fit (1st Order , 2nd Order and 3rd Order Fit )) YouTube
  4. Lecture 04: Prerequisite of Kalman Filter (Repeat) Kalman Filter Fundamentals YouTube
  5. Lecture 05: Kalman Filter Properties YouTube

Week 2

  1. Lecture 06: Target Dynamics Model (Maneuvering & Non-Maneuvering) YouTube
  2. Lecture 07: Sensor Measurement Model and False Alarm Simulation YouTube
  3. Lecture 08: Non linear Kalman Filter Family --- The Extended Kalman Filter YouTube
  4. Lecture 09: Non linear Kalman Filter Family --- The Pseudo-measurement Kalman Filter YouTube
  5. Lecture 10: Pseudo-linear Kalman Filter and Extended Kalman Filter Application In Bearing Angle Only Tracking Problem YouTube

Week 3

  1. Lecture 11: Bearing Angle Only Tracking Problem (contd.) Comparison – PMF vs EKF YouTube
  2. Lecture 12: Statistical linearization and The Unscented Kalman Filter YouTube
  3. Lecture 13: Summary – Explained in Board YouTube
  4. Lecture 14: Introduction to Tracking & Challenges to Multi-Target tracking YouTube
  5. Lecture 15 (Part A): Multi-Target Tracking stages YouTube
  6. Lecture 15 (Part B): Multi-Target Tracking stages (Contd.) YouTube

Week 4

  1. Lecture 16: Nearest Neighbour hood association and Example YouTube
  2. Lecture 17 (Part A): Theory of Probabilistic Data Association YouTube
  3. Lecture 17 (Part B): Theory of Probabilistic Data Association (Contd.) YouTube
  4. Lecture 18: PDAF Implementation including Track Coalescence Problem & Solution YouTube
  5. Lecture 19: Multi Hypothesis Tracking YouTube
  6. Lecture 19 (Part B): Multi Hypothesis Tracking YouTube

Week 5

  1. Lecture 20: Hypothesis Oriented MHT implementation YouTube
  2. Lecture 21: Track-Oriented MHT Concept YouTube
  3. Lecture 22 - Part A: Implementation of Track Oriented MHT YouTube
  4. Lecture 22 - Part B: Implementation of Track Oriented MHT (Contd) YouTube
  5. Lecture 23: Multi-target tracking Algorithm Performance Comparisons YouTube
  6. Lecture 24: MHT Performance Indices YouTube
  7. Lecture 25: Optimal Sub-Pattern Assignment Metric YouTube

Week 6

  1. Lecture 26 - Part A: Concept of Maneuvering Target Tracking and stochastic Hybrid System YouTube
  2. Lecture 26 - Part B: Concept of Maneuvering Target Tracking and stochastic Hybrid System (Contd.) YouTube
  3. Lecture 27: Interacting Multiple Model Algorithm for Maneuvering Target Tracking Stages YouTube
  4. Lecture 28: Problems and Solution for IMM Algorithms YouTube
  5. Lecture 29: Example of IMM tracking YouTube
  6. Lecture 30 - Part A: Application of IMM algorithm for GPS Navigation Problem YouTube
  7. Lecture 30 - Part B: Application of IMM algorithm for GPS Navigation Problem (Contd.) YouTube
  8. Lecture 31 - Part A: GPS Navigation Problem (contd.) YouTube
  9. Lecture 31 - Part B: GPS Navigation Problem (contd.) YouTube

Week 7

  1. Lecture 32: ((GPS Navigation Problem (contd.)) YouTube
  2. Lecture 33: Problems related to target tracking YouTube
  3. Lecture 34: Continuous Kalman Filter Problems YouTube
  4. Lecture 35: Information Filter Problem YouTube
  5. Lecture 36: Implementation of Cramer Rao Lower Bound in target tracking Problems YouTube
  6. Lecture 37: Problems on Bearing Angle only Target Tracking YouTube
  7. Lecture 38: Bearing Angle Only Target Tracking Problem (contd.) YouTube

Week 8

  1. Lecture 39: Part 1 - Introduction to Sensor Fusion YouTube
  2. Lecture 39: Part 2 - Introduction to Sensor Fusion (Contd) YouTube
  3. Lecture 40: Problems Of Measurement Fusion YouTube
  4. Lecture 41: Recursive Estimation using Bayes principle YouTube
  5. Lecture 42: Kalman Filter Based Measurement Augmentation YouTube
  6. Lecture 43: Controller based Measurement Augmentation- Spacecraft Attitude Estimation & Control YouTube
  7. Lecture 44: Part 1 - Controller based Measurement Augmentation - Baro Altimeter Fusion YouTube
  8. Lecture 44: Part 2 - Controller based Measurement Augmentation - Baro Altimeter Fusion (Contd.) YouTube
  9. Lecture 45: Complementary Filter & CBR YouTube

Week 9

  1. Lecture 46: State Vector Fusion YouTube
  2. Lecture 47: Decentralized State Vector Fusion YouTube
  3. Lecture 48: Error Ellipse using Covariance matrix YouTube
  4. Lecture 49 Part A: Introduction to Classification and Machine learning techniques YouTube
  5. Lecture 49 Part B: Introduction to Classification and Machine learning techniques (Contd.) YouTube
  6. Lecture 50: Supervisory learning process flow & Methodologies YouTube

Week 10

  1. Lecture 51: Supervisory learning Methodologies (Naïve Bayes Classifier Example) YouTube
  2. Lecture 52: Supervisory learning Methodologies (Linear Regression) YouTube
  3. Lecture 53: Part A - Supervisory learning Methodologies (Linear Regression Tree) YouTube
  4. Lecture 53: Part B - Supervisory learning Methodologies (Linear Regression Tree) Contd. YouTube
  5. Lecture 54: Supervisory learning Methodologies (Logistic Regression) YouTube
  6. Lecture 55: Logistic Regression Solution Mechanism YouTube

Week 11

  1. Lecture 56: Support Vector machine YouTube
  2. Lecture 57: Support Vector Classifier and Support Vector Machine YouTube
  3. Lecture 58: SVM Optimization solution YouTube
  4. Lecture 59: Fundamentals of Neural Network based classifiers YouTube
  5. Lecture 60: Convolutional Neural Network YouTube

Week 12

  1. Lecture 61: Bias-Variance trade-off in Machine learning YouTube
  2. Lecture 62: Miscellaneous (Problems) YouTube
  3. Lecture 63: Part 1 - Miscellaneous (Problems) YouTube
  4. Lecture 63: Part 2 - Miscellaneous (Problems) Contd. YouTube
  5. Lecture 64 - Conclusion (few practical DTC Systems) YouTube

Syllabus and materials

At NPTEL, as the course publishes them.

Credits and licence

Institution
IIT Kanpur
Department
Multidisciplinary
Teacher
Prof. Anirban Roy
Level
Undergraduate
Language
English
Subjects
Computer science
Source
NPTEL
Licence
CC BY-NC-SA, as NPTEL states it. Non-commercial use only. NPTEL's terms
Attribution
NPTEL states: "Distributed under Creative Commons Attribution-ShareAlike / CC BY - NC - SA", beside a BY-NC-SA badge.
Who can watch
NPTEL gives no rating. Invisible Network shows it to Teens profiles and older, judged from what the source says about it. How courses are placed