Program Plan at a Glance
Total number of credits: 64 (14 Core + 18 Soft Core + 6 Electives+ 26 Thesis Project)
Sem 1 (Aug-Dec)
CP220 (3) (Core)
CP214 (3:1) (Core)
Soft Core (3)
Sem 2 (Jan-Apr)
CP230 (2:1) (Core)
Soft Core (3)
Soft Core (3)
Soft Core (3)
Assignment of Thesis Project Advisor
CP282 (1:2)(Soft Core)
Thesis Project (3)
Sem 3 (Aug-Dec)
Soft Core/Elective (3)
Thesis Project (8)
Sem 4 (Jan-Apr)
Soft Core/Elective (3)
Thesis Project (15)
- 14 Credits are from the mandatory (Core) courses
- List of Soft-Core courses is below
- Electives can be any course offered in IISc (with due permission of the instructor)
Final project will focus on research or technology innovations for industrial or research problems, and will include a mix of analysis, design and implementation.
Note: Explanation of the credits
a:b => ‘a’ hours/week of lectures and ‘b’x 3 hours/week of laboratory work.
Course Contents in Brief
Dynamics of Linear Systems
State space modeling, Linear Systems, Linear Control
Intro to Probability, Linear Algebra, Bayesian Inference, Introduction to Optimization
Autonomous Navigation & Planning
Navigation and planning for autonomous robots
Foundations of Robotics
Modelling and simulation of robots
Exposure to latest topics in research and industry
Soft Core courses & Institute Electives:
Applied Optimal Control and State Estimation
Calculus of Variations & optimal control formulation, Two-point boundary value problems, LQR, STM, SDRE, HJB theory, MPSP design & extension etc
Nonlinear Systems and Control
Consensus over networks with applications in synchronization & opinion dynamics, stabilization over rate limited & quantization channels, Network protocol design, Decentralized optimal control & information patterns, security & privacy in networked control systems
Topics in Networked and Distributed Control
Relevant background topics in control, Estimation & control under communication constraints, event triggered control, connectivity maintenance, security in networked & distributed control systems, applications in robotics & transportation
Vaibhav L./Pavan T
MDP, Reinforcement Learning
Shalabh B/Gugan Thoppe
Jan – Apr
Formal Methods in Computer Science
Model checking, program verification
Design for IoT
Introduction to IoT, Challenges in IoT – Power, Security, Identification, Location, Low Power Design, Energy harvesting systems, Power management algorithms, ARM processor low power features, multiprocessor systems, Lifetime estimation, RFID and its applications, backscattering techniques, Working with protocols such as MQTT, COAP, for low power and energy harvesting sensor nodes, Low power wireless networks – Bluetooth Low Energy (BLE), and IEEE 802.15.4e TSCH. Low Power Wide Area Networks – LORA, NBIoT and power-saving modes, CAT-LTE-M1.
T V Prabhakar
Design of CPS -II
C/C++, Realtime OS, Embedded Programming
Darshak Vasavada/Ashish Joglekar
Replaced by another course CP 316-Real time embedded systems
Design of CPS-I
This is an interdisciplinary course on the design of cyber-physical systems, inviting students from all the departments. It provides an in-depth exposure to various elements of a CPS: the microprocessor, memory and IO devices. The course also includes interfacing sensors and actuators and implementing a control loop. This course uses a practical approach and involves significant C programming on embedded hardware.
Bharadwaj Amrutur/ Darshak Vasavada
Swarm Robotic System
Autonomous operation of Drone/Robots, Swarm Intelligence (Self-Organization & emergence). Motion control, planning, target tracking, predator-prey, formation, Cooperation and Coordination, Market, team theory, game theoretic approaches, decision making under uncertainty
Suresh Sundaram/Jishnu Keshavan
Jan – Apr
Changed to Aug-Dec
Basic psychology of Perception and Motor Action, Collaborative Robots, Introduction to AR/VR and Haptics systems, Facial Expression Recognition, Case studies on HRI
Robot Learning and Control
Machine learning based control for robotic systems
This one to be retained for sake of old students
Robot Learning and Control
Machine learning based control for robotic systems
New one with reduced credits
Perception & Intelligence
Localization & Mapping, Multi-Sensor Perception, Knowledge Representation, Reasoning
Bharadwaj Amrutur/Raghu K
Industrial IoT systems
Industrial protocols such as Time Triggered Ethernet, Time Sensitive Networks, Detnets, Modbus/TCP, PLC systems, Construction of Digital twins, Condition monitoring,
Human Robot Interactions
Introduction; Cross-disciplinary foundation; Hardware and Software components and architecture; Research themes; Building blocks; Navigation, Interaction, Manipulation, and Behavioral aspects for Social Robots; AI for social robots (including Autonomy and Learning for Social Intelligence); Designing a social robot (including Humanoid, mobile and interactive robots); User Studies; Pointers to advanced Topics in the domain.
Pradipta Biswas/Amit Pandey/Sridatta Chatterjee
Formal Analysis and Control of Autonomous Systems
This course will provide an end-to-end overview of different topics involved in designing or analyzing autonomous systems. It begins with different formal modeling frameworks used for autonomous systems including state-space representations (difference equations), hybrid automata, and in general labeled transition systems. It also discusses different ways of formally modeling properties of interest for such systems such as stability, invariance, reachability, and temporal logic properties.
As a next step, the course will cover different techniques on the verification of such systems including Lyapunov functions, reachability, barrier certificates, and potentially model checking. Finally, the course will introduce students to several techniques for designing controllers enforcing properties of interest over autonomous systems.
Real-time Embedded Systems
The course is organized in three parts: standalone (OS less) systems, multi-tasking systems with RTOS and systems with embedded OS. The course involves significant programming in C on embedded platforms running RTOS / embedded Linux.
Part 1: Standalone systems: 4 weeks
Software architecture: control loop, polling and interrupt driven systems, PID control and finite state machine
Experiments: interfacing sensors and actuators to implement a standalone control system on an ARM based hardware platform.
Part 2: Multi-tasking systems: 6 weeks
Introduction to real-time systems, multitasking, scheduling, inter-task communication, memory management and device drivers
Experiments: build a multitasking system involving multiple simultaneous activities involving computing algorithms, IO processing and a user interface.
Part 3: Embedded Linux: 4 weeks
Building an embedded Linux system; processes and threads, memory management, file-system, drivers. Real-time limitations and extensions.
Experiments: build connected application with sensor/actuator front-end and embedded Linux for UI and connectivity.
Pushpak Jagtap/Darshak Vasavada
Theory & Applications of Bayesian Learning
Descriptive Statistics, Introduction to Probabilities, Bayes Rules, Probability Distributions, Maximum Likelihood Estimation, Bayesian Regression and Classification, Expectation Maximization, Frequentist vs Bayesian Learning, Conjugate Priors, Graph Concepts, Bayesian Belief Networks, Probabilistic Graphical Models (PGMs), Probabilistic and Statistical Inferencing, Bayesian Estimation, Structure Learning, Bayesian Optimization, Markov Random Fields, Markov Chain Monte Carlo, PGM examples and applications (including industry and smart cities applications)
Data Science for Smart City Applications
Data types (spatio-temporal data, event data, trajectories, time-series, point-reference etc.), data pre-processing (filtering, discretization, standardization, transformation, Imputation etc.), Regression (linear regression, passion regression), spatio-temporal estimation (kriging, Gaussian process regression etc.), data dissimilarity measures, Pattern discovery (frequent pattern mining, clustering (event, time-series, trajectory clustering, spatio-temporal clustering etc.), Classification (logistic regression, Bayesian classification, SVM, Ensembles), Anomaly/Outlier Detection Techniques, Concepts for big data mining and visualizations (sampling techniques, dimension reduction (PCA, Manifold learning, Self-organizing maps etc.)), Concepts for stream data mining, MapReduce framework.Throughout the course, students will learn to use real data to solve smart city application problems via data science techniques covered in this course.
Experimental Techniques for Robotics& automation
ROS/ROS2, SLAM, Networking, Navigation, Planning, Competition Project
Bharadwaj Amrutur/Ashish Joglekar/Naveen Arulselvan/Kaushik Sampath
Changed from core to soft core
Competition Style, Team Based Robotics Project
Bharadwaj Amrutur/Suresh Sundaram/Pushpak Jagtap
Detection & Estimation Theory
Entrepreneurship, Ethics & Societal Impact
Laboratory Modules (will be embedded in the courses as well as in CP280):
Mobile Robot Programming
Learn to program mobile robots to navigate around an obstacle course
Control of Industrial Robot Arms
Learn to program industrial robot arms to do various tasks like pick and place, movements, gripping, welding etc. Program collaborative arms.
Programming of Drone Systems
Program drones for landing, sorties, pattern flying, etc.
Control robot arms/humanoids over the network.
Robot simulation frameworks
Exercises in Simulation frameworks like PyBullet, Gazebo by creating robot and world models, demonstration of various algorithms
VR/AR & Speech Interfaces
Programming VR/AR, haptics and speech interfaces to machines/robots
Human Robot Interaction
Interfacing Robots with interactive devices like gesture and speech recognition systems, eye gaze tracker, Industrial CoBoT, TeleRobotics, HRI for semi-autonomous vehicle, cognitive load estimation (“human/operator state” might be a broader term?)
ROS/ROS2 Software Stacks
Robot programming using ROS/ROS2
Machine Learning for Robots
ML based Control for Grasping and Manipulation
Robot Sensor and Actuator Systems
Integrate new sensor and actuator system to a robot’s perception system
3D Design and Prototyping for Robotics
3D CAD design, URDF model creation, 3D printing of part and attachment to a robot
Learn to fly drones in IISc testbed
Wheel, IMU, GPS, Lidar, wireless, and combinations by filter-based fusion
Tag-based, landmark-based, feature based, direct methods, deep learning based, monocular and stereo methods
Relevance and Need of the Program
Robotics and autonomous systems are an integral part of Industry 4.0 and robotic automation will see an exponential growth in the future. The shortage of skilled labor in transport, agriculture, and supply chain management; operations in hazardous environment like mines and waste processing and recovery; remote monitoring, space explorations and defense will drive the future of robotic automation solutions. Co-design of Cyber and Physical components of such systems and their safe operation along with humans in unstructured and uncertain environments will be key characteristics of such systems.
Robotics and Autonomous Systems have also changed over the last decade – with the confluence of AI/ML with cheap sensors/Actuators and Battery technologies
With substantial investments by the Govt of India and Govt. Of Karnataka in this area at IISc through the AI & Robotics Park Initiative (ARTPARK), as well as investments from companies like Cisco, Nokia, Garrett etc. via CSR grants – IISc has started developing state of the art experimental facilities in Connected Robots and Autonomous Systems. These facilities to not only support our research, but also develop rich experiential/laboratory-based training programs for the students.
Robotics and Autonomous System has always fascinated our UG students as evidenced by their keen participation in many robotic competitions. However, there is no comprehensive course program in this domain in the country that can train then in the foundational aspects as well as the experimental aspects of the subject.
Key Learning Outcomesof the program
- Foundational concepts in Mathematical Foundations like Linear Algebra, Computational Techniques, Probability and Statistics, Control & Optimization, Statistical Signal Processing, Planning & Decisions, Stochastic and Data driven Control, AI for Robotics, Dynamics & Kinematics, Formal Techniques for CPS
- Applied concepts in Networking for Robotics & Autonomous Systems, Real-Time Embedded Systems, Sensing & Actuation Systems, Applied Machine Learning for Speech & Vision, Reinforcement Learning for Robot Control, Swarm & Team Robotics, Human-Machine Interactions & social robotics, Security, Safety & Privacy for Autonomous Systems, Autonomous ground/air Robots, Navigation & Guidance, Perception via Signal & Image Processing
- Experiential learning via laboratory modules for: Mobile robot programming, Control of Industrial Robot Arms, Programming of Legged Robots, Programming of Drone Systems, Tele-Robotics, Secure Data Pipelines, Robot Simulation Frameworks, VR/AR & Speech Interfaces for Robots, ROS/ROS2 Software stacks, Machine Learning for Robots, Robot hardware for Sensor & Actuator Systems, 3D Design and Prototyping for Robotics, Drone Piloting, Game engine programming, GPU Programming.
RBCCPS under Div. Of Inter-Disciplinary Sciences, is in a unique intersection of Div. Of EECS and Mechanical Sciences and hence can offer such training spanning both the disciplines – and will be the pillar of this program. ARTPark (AI & Robotics Technologies Park) has been incubated by RBCCPS and will provide laboratory support.
How will this program benefit Industry?
Graduates will have a good exposure to foundational and applied topics in Robotics and Autonomous Systems. Hands on exposure to engineering with robots – including mechanical prototyping, ROS/ROS2 programming, AI/ML based programming, VR/AR and other HCI Technologies, 5G and WiFi6 experimentation, indoor and outdoor ground, and aerial robot experiences, will make them well rounded and prepared for many industry problems. They will be able to contribute effectively to create innovative technologies and products in the emerging AI & Robotics applications in industry 4.0, medical, agriculture, mining, defense, smart cities etc.
How will this program benefit academia?
Good theoretical and practical grounding will prepare the graduates of this program to participate in innovative experimental research in Robotics and Autonomous Systems.
Students with UG/PG background in EE, ECE, CS, Mech, Aero and related fields
Target Stakeholder Beneficiaries
Industries in Robotics and Autonomous Systems like: ABB, Bosch, TCS, Wipro, GE, Defense PSUs, Amazon, Flipkart, Target, Nokia, Google, CAIR, ADA, NAL, Intel, Siemens, etc. and many startups
Research Labs in academia like in IISc and IITs.
- Robot Arms,
- Indoor Mobile Robots & Drones,
- Outdoor Mobile Robots & Drones,
- Outdoor autonomous driving testbed
- Indoor Connected Robots Lab
- Humanoid Robots,
- Legged Platforms & Treadmills,
- Indoor Mocap system,
- Indoor Drone Testbed, Windshaping Facility & Indoor Drones,
- Ware-house Robotics Testbed,
- Electronics and Mechanical Prototyping Facilities
As per IISc Norms
- Background Degree: BE, BTech, BS (4years)/Equivalent with Gate about cutoff.
- For Ministry of Education (MOE) Scholarship: GATE neededin one of (EE, EC, ME, AE, IN, CS)
- Sponsored Candidates: Selection as per institute norms
- Selection based on : Gate (70%) + Interview (30%)
30/year for first two years – increasing to 50/year post that. Allot 10% for sponsored students.