Postgraduate Diploma in Semantic Maps and Real-Time Replanning
Online 800-hour Postgraduate Diploma in Semantic Maps and Real-Time Replanning. 8 modules covering ISO 3691-4:2023, ISO 13482:2014 and ROS 2 Nav2. Assigned tutor and enrolment open.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Represent the environment with metric and semantic maps.
Apply semantic detection and segmentation in robots.
Build persistent 3D scene graphs.
Plan routes that take the semantics of the environment into account.
Replan in real time in response to dynamic changes.
Share and merge maps between several robots.
Validate the system in simulation and in real operation.
Who it's for
- Robotics perception engineer who wants to specialise in Semantic Maps and Real-Time Replanning.
- Autonomous navigation engineer who wants to specialise in Semantic Maps and Real-Time Replanning.
- Computer vision engineer who wants to specialise in Semantic Maps and Real-Time Replanning.
- Service robotics developer who wants to specialise in Semantic Maps and Real-Time Replanning.
- Researcher in semantic robotics who wants to specialise in Semantic Maps and Real-Time Replanning.
- AMR fleet integrator who wants to specialise in Semantic Maps and Real-Time Replanning.
- Engineering or science graduates looking to enter logistics.
What you'll work with
- ISO 3691-4:2023
- ISO 13482:2014
- ANSI/RIA R15.08-1-2020
- Regulation (EU) 2024/1689 (AI Act)
- Regulation (EU) 2016/679 (GDPR)
- ISO 8373:2021
8 modules · 800 h
1.1Metric, topological and semantic maps1.2Occupancy maps and OctoMap1.3ESDF distance maps1.43D scene graphs1.5Semantic layers in costmaps1.6Ontologies of indoor spaces1.7Incremental map updating1.8Long-term memory of the environment1.9Real-time requirements1.10Workshop: multilayer map in ROS 2
2.1Object detection with YOLO2.2Semantic and instance segmentation2.3Point cloud segmentation2.42D to 3D projection2.5Surface and zone classification2.6Recognition of doors and signs2.7Detection of people and vehicles2.8Vision-language models2.9Edge deployment with TensorRT2.10Practice: semantic segmentation on an AMR
3.1Semantic fusion in voxels3.2Kimera and Hydra3.3Data Association and Tracking3.4Labeling of rooms and areas3.5Persistent object maps3.6Change of environment and consistency3.7Semantic uncertainty and its spread3.8Map storage and consultation3.9Interfaces for operators3.10Laboratory: Scene graph with Hydra
4.1Costs per semantic class4.2Preference and restriction zones4.3Behaviors according to type of zone4.4Navigation oriented to semantic goals4.5Natural Language Consultations4.6Task planning on scene graphs4.7Social Navigation Rules4.8Integration with Behavior Trees4.9Decision explainability4.10Practice: Costs per zone in Nav2
5.1D* Lite incremental planners5.2Replanning against obstacles5.3Prediction of people's trajectories5.4Planning in dynamic environments5.5Sliding Horizon and MPC5.6Recovery against blockages5.7Map change detection5.8Pipeline Latencies Perception-Plan5.9Computing time guarantees5.10Laboratory: D* Lite in a changing environment
6.1Maps shared between robots6.2Multi-Robot Map Fusion6.3Communication of changes in the environment6.4Central map servers6.5Consistency and versions of maps6.6Bandwidth and compression6.7Fleet System Integration6.8Visual data privacy6.9Map information security6.10Practical Case: Shared Obstacle Update
7.1Semantic quality metrics7.2Field segmentation accuracy7.3Replanning rate and efficiency7.4Tests with people and wheelbarrows7.5Simulation with Isaac Sim and Gazebo7.6Synthetic data generation7.7Security and navigation features7.8Production monitoring7.9Retraining of perception models7.10Practice: Evaluation in simulation with synthetic data
8.1Definition of the environment and tasks8.2Selection of sensors and models8.3Semantic perception pipeline8.4Construction of the semantic map8.5Semantic planning8.6Dynamic replanning in operation8.7Validation in simulation and real8.8Technical report of the semantic system8.9Memory and presentation8.10Final review with the tutor
How you'll learn
100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is ROS 2 Nav2, NVIDIA Isaac Sim, Ultralytics YOLO, OctoMap, Kimera, in free, academic or evaluation versions. Case studies are based on real procedures for building semantic maps in warehouses and hospitals, replanning with dynamic obstacles, and evaluating segmentation with synthetic data. Assessment is continuous per module plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Represent the environment with metric and semantic maps.
Apply semantic detection and segmentation in robots.
Build persistent 3D scene graphs.
Plan routes that take the semantics of the environment into account.
Replan in real time in response to dynamic changes.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- A sufficient level of Spanish to follow technical regulatory texts.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 800 hours, spread over 6 to 8 months. That is between 10 and 15 hours per week on average, compatible with a full-time job.
You will work with ROS 2 Nav2, NVIDIA Isaac Sim, Ultralytics YOLO, OctoMap, Kimera. Free, academic or evaluation versions are used, and the tutor will indicate the open-source alternative where one exists.
An own-award diploma from SEIUM upon passing continuous assessment and the integrating project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area are credited towards the advanced programme. Check the credit transfer policy when enrolling.
Related programmes
Diploma in Batch Automation and Clean Utilities
Online postgraduate diploma of 800 hours in batch automation and clean utilities: 8 modules covering batch process control, recipe and phase design, DCS and PLC implementation,…
Postgraduate Diploma in DfM Design of Mechanical and Vacuum Grippers
Online 800-hour postgraduate diploma in DfM design of mechanical and vacuum grippers. 8 modules covering ISO 9409-1:2004, ISO 10218-2:2025 and SolidWorks. Dedicated tutor and enrolment open.
Diploma in Hygienic Design and CIP/SIP
Online postgraduate diploma of 800 hours in hygienic design and CIP/SIP: 8 modules covering hygienic design principles, materials and finishes, equipment design, CIP and SIP systems,…
More in Robotics, Automation & Control
All Robotics, Automation & Control programmes → · How to apply · Fees & financing · Scholarships