

Internship on Advanced drone AI Controller Development with APSCHE and PHYTEC
Hands-on training includes working with advanced flight controllers such as PX4 and ArduPilot, along with interfacing key sensors like GPS, cameras, LiDAR, and IMUs.
Duration: 16 Weeks
Course Structure:
-
9 Weeks: Hands-on Training
-
6 Weeks: Project Development
-
1 Weeks: Interview Preparation and Personality Development
Detailed Course Content
Week 1-9: Introduction to Robotics and AI • Overview of Robotics • Types of robots (mobile, manipulators, drones, etc.) • Key components: sensors, actuators, controllers • Introduction to AI in Robotics • Role of AI in autonomous systems • Key AI concepts: Machine Learning, Computer Vision, and Reinforcement Learning Week 2: • Tools and Frameworks • Python, ROS (Robot Operating System), and simulation tools (Gazebo, Webots) • Introduction to TensorFlow/PyTorch for AI development • Assignment: Set up development environment and simulate a basic robot. Week 3: Robotics Kinematics and Dynamics • Robot Kinematics • Forward and inverse kinematics for robotic arms • Kinematics for mobile robots • Robot Dynamics • Dynamics of robotic systems • Lagrangian and Newton-Euler formulations • Lab: Implement kinematics and dynamics for a robotic arm in simulation. Week 4: Control Systems for Robotics • Classical Control Methods • PID controllers and tuning • State-space representation and control • Advanced Control Methods • Model Predictive Control (MPC) • Linear Quadratic Regulator (LQR) • Lab: Implement and tune a PID controller for a robotic system. Week 5: AI for Autonomous Navigation • Path Planning and Obstacle Avoidance • Algorithms: A*, RRT, Dijkstra • AI-based path optimization • Sensor Integration • LiDAR, IMU, GPS, and camera data fusion • Lab: Implement a path-planning algorithm in a simulated environment. Week 6: Computer Vision for Robotics • Introduction to Computer Vision • Object detection, tracking, and recognition • OpenCV and YOLO for real-time image processing • Applications in Robotics • Vision-based navigation and manipulation • Obstacle detection using cameras • Lab: Develop a computer vision module for object detection. Week 7: Machine Learning for Robot Control • Reinforcement Learning (RL) for Robot Control • Basics of RL and Q-learning • Training robots in simulated environments • Supervised Learning for Sensor Data • Predictive modeling for robot stability and control • Lab: Train a robot to perform a simple task using RL. Week 8: Advanced AI Techniques • Deep Learning for Autonomous Systems • Neural networks for decision-making • Transfer learning for robotic applications • Swarm Intelligence • Multi-robot coordination and communication • Lab: Implement a neural network for autonomous decision-making. Week 9: Real-World Integration and Testing • Hardware-Software Integration • Deploying AI models on robotic hardware • Real-time testing and debugging • Challenges in Real-World Deployment • Latency, power consumption, and environmental factors • Lab: Test AI controller on a physical robot.
Week 10-16: Capstone Project and Presentation • Capstone Project • Develop an end-to-end AI controller for a specific robotic application (e.g., autonomous navigation, manipulation, etc.) • Integrate all learned concepts: control systems, computer vision, and machine learning • Final Presentation • Demonstrate the project and present findings • Documentation and code submission
Key Deliverables • Weekly lab assignments and mini-projects • A fully functional AI-controlled robotic system (simulated or real-world) • Final report and presentation