PRE2015 4 Groep2

(Wiki markup cheatsheet)

We are developing an autonomous harvesting robot. The robot will be initially developed for harvesting strawberries. As creating a complete prototype is probably not feasible to do in nine weeks, we start with focusing on the detecting and sensing part. For that we will develop a system which scans fruits and determines their ripeness. It can also consider other factors like for example if the fruit looks appealing.

Group 2 members

• Cameron Weibel (0883114)
• Maarten Visscher (0888263)
• Raomi van Rozendaal (0842742)
• Birgit van der Stigchel (0855323)
• Mark de Jong (0896731)
• Yannick Augustijn (0856560)

Requirements

The requirements to add should relate to the detection system? Or do we choose the full robot?

USE aspects

User

Primary users are farmers and their workers, who directly use the robot. The following aspects hold:

• Their work becomes far less intensive and heavy. Instead of directly harvesting, farmers can let the robot do the work. They would now only occasionally need to check the harvest and possibly adjust some parameters. This work is less heavy than harvesting and therefore less health problems due to heavy work can be expected.
• More free time for other things. This is because the new work takes far less time. Also there is no need anymore for training seasonal workers.

Secondary users are distributors that pick up the fruits from the farms. They use the robot occasionally when they need to get the fruits that are picked by the robot. Their work is mostly unaffected, however some parts of their work can be left to the robot, depending on how advanced the robot is. One of these things is selecting fruits based on ripeness and appealing factor. This can be done by the robot. The robot could also directly package and seal the fruits.

A tertiary user is the company that is developing and maintaining this robot. It indirectly uses the robot during development.

(I assume that this is a societal aspect:) Another tertiary user is the harvesting worker. A worker that is harvesting fruit manually does not directly come in contact with the robot. The robot does however influence these workers, as it takes away their jobs. This aspect should be researched more. These harvesting workers are likely people with a low education and students wanting to earn a little more. The people with low education can be expected to have a hard time finding a new job.

Society

See https://drive.google.com/file/d/0BxKlXUVjSWzHV0Y0RWh3UUpGYzg/view?usp=sharing .

Enterprise

See https://drive.google.com/file/d/0Bz2y3nYcBovfX1FBTmdHSzZ1N1k/view?usp=sharing .

Planning

Week 2 Clarifying our project goals
Working on USE aspects
Finalize planning and technical plan
Sketch a prototype

Week 3 Preliminary design for app
First implementation of app
Database/Server setup
CNN, and basics of neural networks

Week 4 App v1.0 with design fully implemented Kinect interfacing to Raspberry Pi completed USEing intensifies Finish back-end design and choose frameworks

Week 5 App v2.0 with design fully implemented and tested Further training of CNN Working database classification (basic) Casing (with studio lighting LED shining on fruit)

Week 6 Improve CNN Expand training sets (outside of strawberries (if possible)) User testing on app Reflect on USE aspects and determine if we still preserve our USE values

Week 7 Implement feedback from testing app Improve aesthetic appeal detection (if time)

Week 8

Week 9 Finish everything Buffer period Final reflection on USE value preservation

Improve wiki for evaluation Peer review

Fallback: App for user to report feedback in the form of images of high/low quality fruit. Have Rpi take pictures using Kinect and send to database Choose a more binary classification (below 50%/above 50% quality) Flesh out the design more (if implementation fails)

Literature

Harvesting robots

• Description of an autonomous cucumber harvesting robot, designed and tested in 2001: http://link.springer.com/article/10.1023/A:1020568125418

• Paper from 1993 describing the then state-of-the-art and economic aspects. It has a chapter on economic evaluation. http://www.sciencedirect.com/science/article/pii/S0021863483710206

(Older)

• Yamamoto, S., et al. "Development of a stationary robotic strawberry harvester with picking mechanism that approaches target fruit from below (Part 1)-Development of the end-effector." Journal of the Japanese Society of Agricultural Machinery 71.6 (2009): 71-78. Link

• Sam Corbett-Davies , Tom Botterill , Richard Green , Valerie Saxton, An expert system for automatically pruning vines, Proceedings of the 27th Conference on Image and Vision Computing New Zealand, November 26-28, 2012, Dunedin, New Zealand Link

• Hayashi, Shigehiko, Katsunobu Ganno, Yukitsugu Ishii, and Itsuo Tanaka. "Robotic Harvesting System for Eggplants." JARQ Japan Agricultural Research Quarterly: JARQ 36.3 (2002): 163-68. Web. Link

• Blasco, J., N. Aleixos, and E. Moltó. "Machine Vision System for Automatic Quality Grading of Fruit." Biosystems Engineering 85.4 (2003): 415-23. Web. Link

• Cubero, Sergio, Nuria Aleixos, Enrique Moltó, Juan Gómez-Sanchis, and Jose Blasco. "Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables." Food Bioprocess Technol Food and Bioprocess Technology 4.4 (2010): 487-504. Web. Link

• Tanigaki, Kanae, et al. "Cherry-harvesting robot." Computers and Electronics in Agriculture 63.1 (2008): 65-72. Direct Dianus
  • Evaluation of a cherry-harvesting robot. It picks by grabbing the peduncle and lifting it upwards.

• Hayashi, Shigehiko, et al. "Evaluation of a strawberry-harvesting robot in a field test." Biosystems Engineering 105.2 (2010): 160-171. Direct Dianus
  • Evaluation of a strawberry-harvesting robot.

State of the art

A small number of tests have been done with machines for harvesting strawberries. These are large, bulky and expensive machines like Agrobot. Cost prices are in the order of 50,000 dollar. Todo: add citations.

A lot of research is done towards inspection by means of machine vision. Todo: add citations and continue.

Further reading

• Agrobot video: https://youtu.be/RKT351pQHfI

• Neural Networks Demystified: https://www.youtube.com/watch?v=bxe2T-V8XRs

• MIT Food Computer: https://www.youtube.com/watch?v=LEx6K4P4GJc

• Dickson Despommier on the vertical farm: https://www.youtube.com/watch?v=XIdP00u2KRA

• Agriculture is the fastest growing robotic sector: http://www.eetimes.com/document.asp?doc_id=1329273

• Japanese firm to open world’s first robot-run farm: http://www.theguardian.com/environment/2016/feb/01/japanese-firm-to-open-worlds-first-robot-run-farm

• Aeroponics (we most likely won’t use this as an irrigation method): https://en.wikipedia.org/wiki/Aeroponics

• Polyculture: https://en.wikipedia.org/wiki/Polyculture

• Why to avoid monoculture: http://evolution.berkeley.edu/evolibrary/article/agriculture_02

• LED lights for imitating sunlight: http://www.gereports.com/post/105532612260/the-future-of-agriculture-indoor-farms-powered-by/

Manual strawberry harvesting process

Source (move to citation)

Notes

Moved to Talk:PRE2015_4_Groep2.