Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Overview of Path Planning for Autonomous Systems
- Fundamental concepts and operational challenges in path planning
- Deployment scenarios within autonomous driving and robotic systems
- Assessment of established and emerging planning methodologies
Graph-Based Path Planning Methods
- Survey of A* and Dijkstra algorithms
- Application of A* for grid-based navigation in government infrastructure
- Adaptive variants: D* and D* Lite for dynamic environments
Sampling-Based Path Planning Methods
- Stochastic sampling strategies: RRT and RRT*
- Path refinement and computational optimization
- Management of non-holonomic motion constraints
Optimization-Based Path Planning
- Formulation of path planning as a constrained optimization task
- Trajectory generation via nonlinear programming
- Gradient-based and derivative-free optimization approaches
Data-Driven Path Planning Approaches
- Deep reinforcement learning (DRL) for trajectory refinement
- Hybrid integration of DRL with conventional algorithms
- Machine learning-driven adaptive navigation systems for government use cases
Navigating Dynamic and Uncertain Conditions
- Reactive planning strategies for real-time operational response
- Obstacle mitigation and predictive control mechanisms
- Incorporation of sensor perception data for enhanced situational awareness
Performance Evaluation and Benchmarking
- Criteria for path efficiency, safety assurance, and computational load
- Simulation and validation frameworks using ROS and Gazebo
- Analytical comparison: RRT* versus D* in complex operational scenarios
Operational Case Studies and Applications
- Navigational strategies for autonomous logistics platforms
- Implementation in self-driving vehicles and unmanned aerial systems
- Practical exercise: Development of an adaptive path planner utilizing RRT*
Conclusion and Future Directions
Requirements
- Competence in Python programming languages
- Practical background in robotics frameworks and control algorithms
- Knowledge of autonomous vehicle technical standards
Audience
- Robotics engineers with expertise in autonomous systems, for government initiatives
- Artificial intelligence researchers engaged in path planning and navigation studies
- Senior-level software developers advancing self-driving vehicle technologies
21 Hours
