Sign up for practicals
Please, form a team of 3 people and write down your names and the day you would like to do the practical in this sign up sheet.
If you didn't manage to find a team, put your name down on the list on the bottom of the sheet and we will assign you to a team.
Mondays 11.00 - 13.00 (Forrest Hill G.A11)
Thursdays 11.00 - 13.00 (Forrest Hill G.A11)
The time allocated for practicals will be used to assess the milestone (subtask) completion, for discussion and resolving issues. The work on the robots is intended to be done mainly outside the practical times. Please respect other classes that might be having practicals in the lab.
How will the practicals be done?
- Decide whether you want to attend the Monday or the Thursday session (by 19/09/2016 - Monday of week 1).
- Form a team of 3 students, collect the kit, and learn how the kit works/connects. (Kit handout - week 1)
- Build a robot and start programming it. Ask the demonstrators if you require help with mechanics, electronics, or programming.
- Work on minor milestones in your own time and discuss them during the lab sessions ( week 2 - week 4)
- Demonstrate your work on major milestone 1 during the lab session (week 5)
- Work on minor milestones in your own time and discuss them during the lab sessions ( week 5 - week 8)
- Demonstrate your work on major milestone 2 during the lab session (week 9)
- Submit the final report (21/11/2016 - Monday of Week 10)
- Dismantle the robot and return the kit (24/11/2016 - Thursday of Week 10)
There will be a written homework due on Friday 11th November (week 8) as part of this course and you will have to manage your workload between different courses, so plan your time accordingly!
robot is expected to move around the arena in the lab and collect as many
resources (textured boxes) as it can (3 resources will be provided). The arena contains two base location marked with a black cardboard on the floor. Each resource belongs to only one of these bases. Resources will
be marked with a different pattern/texture unique to the base it belongs to. The allocation of resources to bases will be given. The shape (map) of the arena will be provided (i.e. you can build a map of the arena).
The robot should use the camera to identify the resources and
the robot position
in the arena.
There will be only one robot in the arena during the demonstrations.
The final goal of this practical is to collect all three resources in under 5 minutes time. The robot will have to move around the arena, avoid obstacles, localize itself within the arena, identify the resources, collect them and bring them to the correct base.
There are two identical arenas in the lab to provide more space for multiple teams running experiments/demos simultaneously.
The marking scheme for the course is:
Exam - 50%
Homework - 10%
Practical - 40%
Each major milestone will be marked on the day based on quality of the demonstrated material. Each group will demonstrate their solution to the problems marked in the corresponding milestone. Completion of some tasks requires the completion of previous tasks, e.g. to demonstrate collision avoidance, navigation is required. You are free to demonstrate multiple tasks at the same time and you will be marked for all demonstrated tasks. This is the preferred way. Each group will also explain the implemented techniques verbally.
Together with the major milestones (1 and 2), each GROUP will submit a short report describing their implementation using bullet points (one report per group highlighting the techniques used).
Minor milestones are not marked.
The largest chunk of the marks will be given based on the individual final report that will be handed in by the date shown in the schedule to the ITO (and using the DICE submit system).
The practical marking scheme:
Major milestone 1 - 12%
- 1% - Navigation (speed and direction control)
- 2% - Collision avoidance (around obstacles of different sizes and narrow corridors)
- 2% - Detecting objects of interest from a long distance (~1m).
- 3% - Identifying the resource at sort distance (~0.4m).
- 3% - Robustness (repeat the resource identification 4 times in a row with different resources)
- 1% - Short report and verbal description of the work (this is a group report)
Major milestone 2 - 12%
- 1% - Localization (correctly identify current room)
- 2% - Homing (navigate to the a specific home base from an arbitrary start location).
- 1% - Visual servoing (drive to and pick up a resource from a short distance ~0.4m).
- 1% - Integration of all milestone tasks (MMS1 and MMS2).
- 1% - Deliver 1 resource to the correct base (within 5 minutes).
- 2% - Deliver 2 resources to the correct base (within 5 minutes).
- 3% - Deliver 3 resources to the correct base (within 5 minutes).
- 1% - Short report and verbal description of the work (this is a group report)
- Final report - 16%
- Evaluation - 10% (Individual analysis of the performance and choices made throughout the design process)
- Writing - 6% (this includes, quality of the description of the methods used, clarity and completeness, justification of methods used)
- The report will be submitted INDIVIDUALLY by each student (NO group submissions).
- All marks are percentage of the total mark for the whole course.
There are types of milestones: major and minor.
- The minor milestones will help you to stay on track with the work on weekly basis but they are NOT marked. If you fall behind on the minor milestones, you may catch up the next week without any penalty. We do strongly recommend to keep up to speed with the minor milestones and we encourage you to discuss them with the demonstrators during the lab sessions regularly.
- The major milestones will be used to evaluate your progress and the are marked.
If you fall behind on the major milestones, you will loose marks. You
will have to demo your work during the practical time slot. Late
submission are not allowed!
Subsequent tasks must include subtasks you have completed in the previous weeks. For example, a robot able to identify the resources should still be able to avoid obstacles.
After completing the major milestone, we will provide a example solution. You can use this solution to improve your own code (if the example performs better than your own) or you can use it to catch up if you have fallen behind on your work.
Week 3 - Minor - Autonomous operation
- Suitable mechanical design.
- Forward and turning motion.
- Autonomous operation - no connection to the network.
- Capturing pictures using the camera.
Week 4 - Minor - Collision free navigation
- Obstacle avoidance.
- Recovery when obstacle avoidance fails.
- Avoid getting stuck.
- Object classification using vision from a short distance (~0.4m).
Week 5 - MAJOR MILESTONE 1 - Localisation and resource identification
- Collision avoidance.
Navigate the robot around resources and obstacles without getting stuck.
- Resource classification.
Use vision to identify resources and calculate their location w.r.t. the robot.
Week 6 - Minor -
- Autonomous operation - no connection to the network (moving and turning).
- Navigate from room A to room B without collisions of successfully recovering from collisions.
- Correctly identify the room the robot is in.
- Full marks will be given when the robot can localize itself (identify room A) and navigate to room B without collisions (or getting stuck) and intervention.
Week 7 - minor - Resource localisation
- Find resources in the current room, distinguishing them from other objects (possibly from far away).
- Explore the room if necessary.
- Report that the room contains useful resources or that it is empty and another room should be explored.
Week 8 - Minor - Resource identification and collection
- Distinguish between resource types (you can assume the resource if fairly close at this point).
- Localize an resource of interest.
- Approach the resource and collect/trap it.
Week 9 - MAJOR MILESTONE 2
- Localization and homing.
Correctly identify the room the robot is in and navigate to a specific base.
- Visual servoing.
Control the robot to collect a resource that has been previously identified at a short distance (~0.4m).
- Integration and collection of multiple resources.
Collect and deliver ap to 3 resources within 5 minutes.
Week 10 - Final report and kit collection
- By 4pm, submit a printed copy of the final report to ITO and an electronic copy via the "submit" command on DICE:
submit rss 2 <file1>
- Dismantle the robot, return the kit, locker keys and collect the deposit.
Advice on writing final report
The final report will be written individually and it will contain complete description of the robot developed during the course. The milestone reports will be reused and expanded upon in the final report. This is where the overlap between work done by individual team members will be present and permitted. The rest of the report will be completely individual, e.g. introduction, problem description,evaluation, conclusion.
Note that most of the marks for the practicals come from the write-up of the final report. It may help to think of this as a (short) equivalent of how robot projects are reported in scientific papers, for example. Here's an outline of what your report should contain:
Title: A 4-12 word title that would allow an unfamiliar reader to know what your report is about.
Abstract: You MUST preface the report with a 100-200 word summary of what it contains. This is usually easier to write when you have finished the report. It should briefly explain the task, the approach used, the results and the conclusions drawn. Avoid making entirely generic statements that could apply to almost anything, e.g., (BAD) "This report describes the construction of a robot to perform a task. We describe the design decisions and outline the control program, then explain the results and possible improvements". Instead make it specific to what you have done, e.g., (GOOD) "We have built a robot capable of searching for and recognising special locations in a lab environment. It uses two IR sensors to avoid obstacles, and a low cost camera to recognise resources and target locations, as well as a sonar sensor for navigation. We implement a subsumption control architecture. The robot was tested in five time trials and was able to locate an average of 4 resources and 3 target locations within that time. The main limitation was that our robot was unable to reliably plan its route to the next location but relied on random search".
Introduction: This should explain the task, and give an overview of how you approached it. In a normal scientific report this would include reference to previous work (your own or others). You are not required in this case to refer to other work (although you may wish to do so if for example something you read about influenced your approach to the task). So this section is likely to be quite short (400 words).
Methods: A good rule of thumb here is that someone reading your report should be able to replicate your approach. So you need to provide a good description of the physical architecture, particularly the type, number and position of sensors and actuators. Include labelled photographs or diagrams, and make sure the dimensions are clear. Comment on factors that led to the design, explaining the decisions you made. For the control program you should provide a flow diagram or pseudo-code description, and again explain the reasoning that led to this solution. This is likely to be the longest section of the report. Do not include code except for short snippets that help explain a crucial part of the program you created. Avoid repetition and refer to other peoples' work instead of describing well known algorithms. (1400 words)
Results: This should contain some quantitative evaluation of the robot performance. For example: that it can find a resource site from a disance of x metres, and recognise and leave within t seconds; etc. If your robot is not capable of doing the final task, you should evaluate what it does do correctly, and try to analyse what it does wrong. The reader should be left with an accurate understanding of exactly what your robot is capable of, even if this is not as good as you hoped. Bad results are results too. You get marked based on how you approached the problem and how you evaluated the results. (800 words)
Discussion: Start by summarising the results, and giving your evaluation of how well it works. Explain what you think were the most successful elements of your approach, and what was less successful. Include ideas about how the system could be improved. (200 words)
Length: The final report should be no more than 3000 words long. It can be shorter if you think that you can do a satisfactory description in fewer words.