Designing an Artificial Cooking Machine for Enhanced Cooking

Experience

Jingbin Ben Chen

Guangzhou Foreign Language School, Guangzhou, China

Keywords: Cooking Robotic, Automate, System, Intelligent.

Abstract: Eating plays a vital role in people's lives, but the demands of a fast-paced lifestyle often hinder individuals,

especially the elderly, from cooking nutritious meals at home. To address this issue, an intelligent self-cooking

robotic arm can be designed to automate the process of cutting vegetables and frying dishes, providing a

convenient solution for individuals who are not present in the kitchen. This paper draws inspiration from

existing cooking robots to propose a more advanced robotic arm capable of performing various cooking

methods with increased efficiency and convenience. The design focuses on creating a mechanical product that

caters to the needs of the modern population, aiming to enhance their cooking experience. The paper discusses

the structural framework and internal system required for the development of this intelligent cooking robot.

1 INTRODUCTION

The impact of automation and robotics has

significantly permeated the kitchen landscape as socio-

economic factors, changing work patterns, and recent

global events like the COVID-19 pandemic have

driven the need for more efficient and contactless

cooking solutions. As individuals grapple with

balancing work-from-home arrangements and

household chores, the demand for automated kitchen

appliances, including cooking robots, has surged. The

current market for cooking robots is varied, with

brands offering models that range from basic cooking

functions to more sophisticated units capable of

replicating intricate culinary techniques. Brands like

Moley Robotics, Nymble, and Thermomix are paving

the way in this burgeoning industry. However, while

these models offer a promise of convenience, they

often come with limitations such as high price points,

bulky sizes, and complex user interfaces (Singh et al

2021).

1.1 Basic Situations

The evolution of cooking robots can be traced back to

rudimentary devices that performed simple tasks such

as stirring and basic chopping. These initial versions

of cooking robots were limited in their capabilities,

primarily designed to automate routine tasks and

reduce human effort in the kitchen (Garcia-Haro et al

2020). Their functions were often programmable but

relied heavily on manual user input and had limited

adaptability. Still, they represented the first steps

toward the automation of cooking processes,

providing a foundation for the more advanced models

we see today.

Over time, the capabilities of cooking robots have

expanded significantly due to advancements in

technology and a better understanding of user needs

and expectations. Today's cooking robots come

equipped with advanced features such as ingredient

recognition and programmed recipes (Pereira,

Bozzato et al 2022). These robots are capable of

performing more complex tasks, such as measuring

ingredients, stirring at different speeds, and even

following a pre-programmed recipe to create a dish

from start to finish (Pereira, Pra et al 2022).

However, despite these advancements,

contemporary cooking robots often encounter

challenges when it comes to tasks requiring finer motor

skills or judgment calls. For example, adjusting

cooking times based on the size or amount of

ingredients is a task that most current models struggle

with. Similarly, tasks like finely chopping vegetables,

carefully stirring delicate ingredients, or assessing

when a dish is perfectly cooked, are still outside the

reach of many cooking robots (Ramirez-Alpizar et al

2021). These areas highlight the limitations of current

Chen, J.

Designing an Artiﬁcial Cooking Machine for Enhanced Cooking Experience.

DOI: 10.5220/0012816700003885

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Data Analysis and Machine Learning (DAML 2023), pages 397-401

ISBN: 978-989-758-705-4

397

technology and provide a clear direction for further

improvements.

Livinsa et al. made a significant contribution to

the field of cooking automation with their proposed

model of a cooking robot (Livinsa et al 2021). This

model uses the Arduino Mega platform for complete

automation, providing a high degree of control and

programmability (Kusriyanto and Putra 2018). The

robot is capable of performing a variety of kitchen

tasks, including ingredient pumping, stirring, and

cooking. By automating these tasks, the robot vastly

reduces the time and effort required from the user,

making the cooking process more efficient and less

labor-intensive. This model represents a substantial

leap forward in cooking automation. However, it's not

without its shortcomings. Aspects such as the user

interface could be improved to provide a more

intuitive and user-friendly experience. Currently,

users may find the interface complex and difficult to

navigate, which can lead to frustration and a

reluctance to utilize the robot's full capabilities.

Furthermore, while the robot offers a degree of

flexibility in cooking methods, there is scope for

further enhancement. A wider range of programmable

cooking techniques would allow the robot to cater to

a broader array of cuisines and recipes, greatly

increasing its versatility and appeal (Wang et al

2019). Finally, the integration of the robot with smart

home systems represents another area for

improvement. As smart homes become increasingly

common, the ability to seamlessly integrate with

other devices and systems in the home could greatly

enhance the robot's functionality and user-

friendliness (Wilson et al 2019).

In summary, while the Livinsa et al. model

represents a significant advancement in the field of

cooking robots, there is still considerable potential for

further improvement and innovation. With ongoing

research and development, future models will

undoubtedly continue to push the boundaries of what

is possible in cooking automation.

1.2 Future Opportunities

In the contemporary fast-paced society, the number of

individuals engaged in office work or other

demanding professional sectors has seen a steep rise.

The hectic schedules and demanding lifestyle often

leave these individuals with little or no time to engage

in cooking. This scarcity of time, coupled with

limited cooking skills in some instances, has led to an

increased reliance on outside food. However, this

dependence on commercially prepared meals is not

without its health implications. Commercially

prepared meals often contain high levels of salt, oil,

and sugar, along with various food additives. The

excessive intake of these substances can have adverse

effects on health, placing undue strain on several vital

body systems (Nadathur et al 2016). For instance,

high salt content can contribute to hypertension and

strain the cardiovascular system. Excessive oil,

especially if it is saturated or trans fats, can lead to

obesity and cardiovascular diseases. High sugar

content can lead to insulin resistance and eventual

diabetes. Moreover, various additives commonly

used in commercial meals can affect the digestive

system, leading to various intestinal issues.

Recognizing these health concerns and the need to

overcome time constraints and limited cooking skills,

the kitchen appliance industry has made significant

strides. A variety of innovative appliances have been

introduced to facilitate home cooking without

requiring significant time or culinary expertise. For

instance, multi-function cooking machines, as

discussed by Livinsa et al., have emerged as a popular

solution (Livinsa et al 2021). These machines

combine the functions of several kitchen appliances,

capable of weighing, chopping, cooking, grinding,

and stirring. This multi-functionality not only saves

space in the kitchen but also simplifies the cooking

process, making it more accessible to those who

might be intimidated by traditional cooking methods.

Another promising development in this space is

the advent of mobile cooking robots (Yamamoto et al

2019). These robots can perform a range of cooking

tasks, significantly reducing the time and effort

required for cooking. By automating the cooking

process, these robots allow individuals to use their

time more effectively, freeing them from the need to

spend extended periods in the kitchen. Automated

cooking robots represent a convenient and efficient

solution for home cooking. By improving the quality

of dishes and reducing the labor burden, these robots

bring the joy of delicious, home-cooked meals to

those with busy schedules. They offer a hassle-free

cooking experience, allowing individuals to enjoy

nutritious and personalized meals without having to

compromise their health or their time. In essence,

these innovations are bridging the gap between

convenience and health, providing a viable alternative

to the over-reliance on commercially prepared meals.

DAML 2023 - International Conference on Data Analysis and Machine Learning

398

2 CLASSIFICATION AND

SOLUTIONS FOR COOKING

ROBOTS

2.1 Classification of Cooking Robots

In the realm of cooking automation, robots are

primarily classified into two types: fully automated

and semi-automatic cooking robots (Bock et al 2019).

Fully automated cooking robots, such as the

Moley Robotic Kitchen, are designed to handle the

entire cooking process independently, from prepping

ingredients to cooking and even cleaning up. These

robots are typically integrated into a kitchen set-up

and include robotic arms, an oven, a stove, and other

necessary appliances. They offer a luxurious, hands-

off cooking experience ideal for individuals who

prefer minimal involvement in the kitchen. However,

their high cost and complex installation requirements

limit their widespread adoption.

Semi-automatic cooking robots, on the other

hand, like the Thermomix TM6, are compact

countertop devices that can perform multiple cooking

tasks. While they cannot operate entirely

independently, they provide substantial aid in the

kitchen, performing functions like chopping, stirring,

and cooking. These robots are popular due to their

affordability, ease of use, and versatility in cooking a

wide range of dishes.

In terms of mixing methods, cooking robots can

employ several techniques depending on the specific

requirements of the dish. Active stirring is a common

method used in robots designed for dishes that need

uniform stirring, such as fried rice and stir-fried

noodles. For example, the HomeCooker from Philips

uses active stirring to ensure even cooking. Passive

stirring, on the other hand, is a method often seen in

appliances like the Tefal Actifry. It uses a stirring

paddle that moves with the pan, somewhat like a

washing machine. This method is advantageous for

dishes that require specific mixing techniques, such

as stir-frying seasonings or gently tossing ingredients

without breaking them.

Other robots, like the June Oven, use a different

approach altogether, employing convection heat and

internal cameras to cook and monitor the food,

eliminating the need for stirring. As the field of

cooking automation continues to evolve, we can

anticipate the emergence of more sophisticated

mixing methods and cooking techniques, providing a

richer and more convenient cooking experience.

2.2 Specific Solutions

Optimizing the rotation angle and angular speed of

the cooking robots' arm or stirring mechanism is key

to achieving efficient and effective cooking. This

optimization can be approached through control

theory principles and kinematic analysis. For

example, the rotational motion of the robot arm can

be described using the equation 1 (used in Figure 1):

θ = θ

+ ω

t + 0.5αt^2 (1)

where θ is the rotation angle, θ

is the initial rotation

angle, ω

is the initial angular speed, α is the angular

acceleration, and t is the time. By adjusting the

angular speed (ω

) and the angular acceleration (α),

the robot can adapt its rotation angle (θ) effectively to

the required cooking task.

To identify and manipulate food items, a

Simultaneous Localization and Mapping (SLAM)

system can be employed (see Figure 2) (Stachniss et

al 2016). This technology is often used in autonomous

vehicles and drones for navigation. In the context of

cooking robots, a SLAM system can perform object

recognition, allowing the robot to identify different

food items. The SLAM system uses a combination of

sensors (like LiDAR or sonar) and cameras to create

a map of the environment and track the robot's

location within it. Machine learning algorithms can

be trained on a dataset of food images to enable the

robot to identify different ingredients.

However, the use of SLAM in cooking robots

comes with its limitations. It requires a significant

amount of processing power and a large, high-quality

dataset for reliable food recognition. Lighting

conditions and the appearance of food items can vary

greatly, complicating the task of accurate

identification. Additionally, the system may struggle

with identifying and manipulating food items that

have similar colors or shapes. As technology

advances, these limitations can be mitigated through

improved sensor technology, more powerful

processors, and more sophisticated machine learning

algorithms.

Figure 1: The models of smart cooking stir-fry machines on

the market.

Designing an Artiﬁcial Cooking Machine for Enhanced Cooking Experience

399

Figure 2: The sensors that used to identify food via taking

photos and maps in real time.

2.3 Challenges and Safety

Considerations

Despite the promise of convenience, cooking robots,

like any other automated system, are not devoid of

safety incidents. For example, in 2016, a Thermomix

TM31 unit reportedly caused several burn incidents

due to a faulty sealing ring that allowed hot food and

steam to escape. Safety considerations in the design

and operation of cooking robots are paramount to

prevent such incidents. These safety measures can be

broadly categorized into hardware safety features and

algorithmic safety features.

Hardware safety features include design elements

such as robust sealing systems, sturdy build quality,

and safety locks (Anderson 2020). These features are

designed to prevent physical accidents like burns,

cuts, and spills. Additionally, overheat protection

measures, such as temperature sensors and automatic

shut-off features, can prevent overheating, a common

issue in kitchen appliances.

Algorithmic safety features refer to the software-

level safety measures implemented in the machine's

operating system (Fernández et al 2021). One such

feature could be a fall-back mechanism in the control

system that stops the robot's operation if it detects an

anomaly. This could be achieved using a watchdog

timer, a common safety feature in embedded systems.

If the system does not reset the watchdog timer within

a certain period (indicating that it's operating

correctly), the timer triggers a system reset or a safe

shutdown.

Another algorithmic safety measure could be an

emergency stop (E-Stop) feature, which allows the

user or the system itself to halt operations

immediately in case of a perceived risk. This could be

a physical button on the robot or a command in the

user interface. Algorithmic safety features would also

include error detection and fault tolerance methods.

For example, the robot could be programmed to

recognize when a cooking pot is not correctly placed,

preventing it from starting a cooking process that

could lead to a spill or burn.

As cooking robots continue to evolve, the

integration of advanced sensor technology and

machine learning can significantly enhance safety.

For instance, predictive analytics could be used to

anticipate potential hazards and proactively address

them, leading to safer and more reliable cooking

experiences.

3 CONCLUSION

The proposed design of an advanced robotic arm for

cooking automation differentiates itself from existing

solutions by focusing on user-centric design,

flexibility in cooking methods, and seamless

integration with smart home systems. While current

solutions offer a range of functionalities, they often

fall short in terms of intuitive user interfaces and

versatility in cooking techniques. The proposed

design seeks to address these gaps, providing a more

personalized and engaging cooking experience. By

optimizing the rotation angle and angular speed of the

robot arm, the system can adapt to a wide range of

cooking techniques, allowing for more diverse and

complex dishes. Additionally, the use of a SLAM

system for ingredient recognition opens up

possibilities for more intelligent and autonomous

cooking processes.

Safety is a paramount concern in the proposed

design. By incorporating both hardware and

algorithmic safety measures, the system aims to

provide a secure cooking environment that minimizes

the risk of accidents. This focus on safety, combined

with user-friendly design characteristics, sets the

proposed solution apart from existing market

offerings. The potential impact of this proposed

solution is multifaceted. For users, it promises a more

convenient and enjoyable cooking experience, with

the added benefit of healthier, home-cooked meals.

For the elderly or those with physical disabilities, the

proposed design could provide invaluable assistance,

making cooking more accessible. On the market

level, this innovative approach could stimulate further

advancements in the field of cooking automation,

leading to products that are even more intelligent,

versatile, and user-friendly. As consumer

expectations evolve, there will be an increasing

demand for solutions that not only automate cooking

but also make it an engaging and personalized

experience. The proposed design aims to meet this

demand, paving the way for the next generation of

cooking robots.

In conclusion, while there are challenges to

overcome, the potential benefits of an advanced

DAML 2023 - International Conference on Data Analysis and Machine Learning

400

cooking robot as proposed in this paper are

significant. With further research and development,

we can move closer to a future where cooking is not

a chore, but a seamless and enjoyable part of our daily

lives.

REFERENCES

Singh A, Chavan A, Kariwall V, Sharma C. A systematic

review of automated cooking machines and foodservice

robots. In2021 International Conference on

Communication information and Computing

Technology (ICCICT) 2021 Jun 25 (pp. 1-6). IEEE.

Garcia-Haro JM, Oña ED, Hernandez-Vicen J, Martinez S,

Balaguer C. Service robots in catering applications: A

review and future challenges. Electronics. 2020 Dec

30;10(1):47.

Pereira D, Bozzato A, Dario P, Ciuti G. Towards

Foodservice Robotics: a taxonomy of actions of

foodservice workers and a critical review of supportive

technology. IEEE Transactions on Automation Science

and Engineering. 2022 Jan 21;19(3):1820-58.

Pereira D, De Pra Y, Tiberi E, Monaco V, Dario P, Ciuti G.

Flipping food during grilling tasks, a dataset of utensils

kinematics and dynamics, food pose and subject gaze.

Scientific Data. 2022 Jan 12;9(1):5.

Ramirez-Alpizar IG, Hiraki R, Harada K. Cooking Actions

Inference based on Ingredient’s Physical Features.

In2021 IEEE/SICE International Symposium on

System Integration (SII) 2021 Jan 11 (pp. 195-200).

IEEE.

Livinsa ZM, Valantina GM, Premi MG, Sheeba GM. A

modern automatic cooking machine using arduino

mega and IOT. InJournal of Physics: Conference Series

2021 Mar 1 (Vol. 1770, No. 1, p. 012027). IOP

Publishing.

Kusriyanto M, Putra AA. Weather station design using IoT

platform based on Arduino mega. In2018 International

Symposium on Electronics and Smart Devices (ISESD)

2018 Oct 23 (pp. 1-4). IEEE.

Wang L, Zhang X, Xia Y, Zhao X, Xue Z, Sui K, Dong X,

Wang D. Cooking‐inspired versatile design of an

ultrastrong and tough polysaccharide hydrogel through

programmed supramolecular interactions. Advanced

Materials. 2019 Oct;31(41):1902381.

Wilson G, Pereyda C, Raghunath N, de la Cruz G, Goel S,

Nesaei S, Minor B, Schmitter-Edgecombe M, Taylor

ME, Cook DJ. Robot-enabled support of daily activities

in smart home environments. Cognitive Systems

Research. 2019 May 1;54:258-72.

Nadathur S, Wanasundara JP, Scanlin L, editors.

Sustainable protein sources. Academic Press; 2016 Oct

Yamamoto T, Terada K, Ochiai A, Saito F, Asahara Y,

Murase K. Development of human support robot as the

research platform of a domestic mobile manipulator.

ROBOMECH journal. 2019 Dec;6(1):1-5.

Bock T, Linner T, Güttler J, Iturralde K. Ambient

Integrated Robotics: Automation and Robotic

Technologies for Maintenance, Assistance, and

Service. Cambridge University Press; 2019 Aug 29.

Stachniss C, Leonard JJ, Thrun S. Simultaneous

localization and mapping. Springer handbook of

robotics. 2016:1153-76.

https://www.lanxincn.com/en/system.html

https://leadstov.com/commercial-automatic-stir-frying-

cooking-machine-lt-tgq30/

Anderson R. Security engineering: a guide to building

dependable distributed systems. John Wiley & Sons;

2020 Nov 25.

Fernández J, Perez J, Agirre I, Allende I, Abella J, Cazorla

FJ. Towards functional safety compliance of matrix–

matrix multiplication for machine learning-based

autonomous systems. Journal of Systems Architecture.

2021 Dec 1;121:102298.

Designing an Artiﬁcial Cooking Machine for Enhanced Cooking Experience

401