Industrial Automation Magazine India

Increased payload capacity brings cobots closer to conventional robots

Published on : Monday 05-06-2023

R Vijayalayan, Senior Manager, Application Engg – Automotive Industry & Control Design, MathWorks.

Cobots, as we understand them today, have been around for 15 years. How disruptive has this development proved in the field of robotics?
In conventional industry automation, robots must be separated from physical human contact to ensure reliable functionality without causing bodily harm to human operators. In these systems, robots operate in entirely human-free zones or within cages.

Here are a few things to consider:
 
Flexible Automation
Constraining robots in cages limits their capabilities. Current markets demand reduced lead times and mass customisation. These demands have stimulated interest in flexible and multipurpose manufacturing systems through human and robot collaborations that do not endanger workers. In flexible and collaborative automation, cobots augment and enhance human capabilities with strength, precision, and data analytic capabilities that add value for the cobot end-users. Cobot development aims for:
i. Coexistence — shared workspace with human workers to optimise a process, and
ii. Collaboration — flexible automation for various tasks with human engagement.
 
Safety Systems
Safety fences present a technological barrier to the broader adoption of robots. Cobots are designed to satisfy safety requirements with intrinsic safety designs that allow safe interaction between the cobot and objects in its workspace (e.g., the ISO® 10218-1 standard). Cobots reduce the inertia exposed in potential collisions and contain compliant components such as joint torque sensors to absorb the energy of undesired impacts. Furthermore, cobot developers employ many external sensors (e.g., cameras, laser, depth, etc.), and fuse the acquired data to enable reliable recognition of human-robot proximity and gestures.
 
Cobot Programming with Advanced Algorithms and AI
There are cobot applications and technology gaps that hinder full cobot deployment. Advanced algorithms are needed for cobots to achieve their great potential for manufacturing in high-mix, low-volume production environments. Cobots must be able to perform in unfamiliar situations without explicit instructions by perceiving their environment using deep learning. The cobot’s motion planner allows the cobot to achieve a target position, and collision avoidance algorithms perform reactive behaviour in dynamic environments based on local knowledge provided by sensors as the cobot moves. Then, AI will allow the realisation of a lot more advanced cobot applications. It empowers cobots with advanced perception, decision-making, learning, and communication capabilities. Integrating AI technologies with cobots enables them to operate more intelligently, autonomously, and effectively in various applications, ultimately improving their performance and productivity in a collaborative manner.
 
Cobots have proved the sceptics wrong in adapting to various tasks. What explains this popularity? What are the other leading applications?

A collaborative robot (cobot) is a robot that allows humans to work alongside the robot through direct interaction without conventional safeguarding fences. The benefits of direct human interaction with cobots enable:
i. Safe execution of complex tasks
ii. High production quality, and
iii. Intuitive and user-friendly teaching and programming of cobots.
 
The concept of cobots, or ‘intelligent assist devices’, emerged from research projects and companies in the automotive industry, where they provided the power to move heavy objects under human control through direct interfaces. These systems ensured the safe usage of cobots’ assistive capabilities. Over the years, cobots have been developed to perform tasks including:
i. Pick and place
ii. Quality inspection
iii. Last-mile assembly and finishing, such as grinding, sanding, and painting, and
iv. Massive range of manufacturing applications, from welding, machine tending, and screw-driving through inspection, packaging, and palletising.
 
In addition to the tasks mentioned earlier, cobots have found applications in various industries. Some of the leading applications include: 
a. Healthcare: Cobots are used in healthcare settings for medication delivery, patient monitoring, laboratory assistance, and surgical assistance.
b. Agriculture: Cobots find applications in agricultural tasks such as planting, harvesting, pruning, and sorting.
c. Retail: Cobots are used in retail environments for shelf stocking, inventory management, and customer assistance.
d. Service: Cobots are utilised in the hospitality industry for tasks like cleaning, room service, and concierge services.
 
How does MATLAB help promote the use of cobots, particularly the programming part?
Robotics engineers use MATLAB for advanced robot application development that incorporates deep learning, computer vision, optimisation, and sensor fusion to understand dynamic ambient. They do this by: 
- Creating digital twins of robots and performing modelling and simulation to verify the entire workflow. 
 
- MATLAB's AI capabilities and sophisticated robot algorithms allow robots to better perceive dynamically changing workspaces to move more efficiently and productively.
 
- Engineers can also verify their robot applications by connecting with robot hardware, like Universal robots cobot. 
 
What is the significance of MATLAB’s collaboration with Universal Robots and its implications for the industry?
MathWorks joined the UR+ program, the industry’s largest and most comprehensive ecosystem of products certified to integrate seamlessly with cobots from Universal Robots (UR). MathWorks received the UR+ certification for MATLAB, a programming and numeric computing platform that provides software tools and algorithms for designing, simulating, testing, and deploying robotics applications, including those for Universal Robots’ cobots.
 
Robotics engineers use MATLAB for specialised or sophisticated cobot applications that are difficult to program using the UR teach pendant or graphical-based programming tools, including applications that incorporate machine learning, deep learning, computer vision, optimisation, sensor fusion, and advanced signal processing. MATLAB provides AI capabilities for cobots to move more efficiently and productively by perceiving dynamically changing workspaces and sophisticated robot algorithms. Engineers can verify their UR cobot applications by connecting MATLAB to URSim, a simulation software for robot programs, or UR hardware. MATLAB support for Universal Robots is compatible with the entire e- and CB-series of Universal Robots.
 
This partnership offers robotics engineers AI and autonomy capabilities in programming and helps simplify complex cobot deployments. Offline cobot programming and simulation within MATLAB enables users to minimise downtime when programming using robots on-site.  Robotics engineers can also deploy robotic algorithms and AI models by generating C++ codes directly on embedded targets, such as GPU boards, using MATLAB Coder™ and Simulink Coder™ for standalone, accelerated execution with UR hardware.  
 
With Universal Robots’ market leadership and MATLAB and Simulink's ability to accelerate the pace of innovation, integrators and end users will now have the ability to solve more complex automation workflows. The UR hardware support package reduces the time to market for advanced cobot applications that require the integration of multiple complex technologies. This enables small- and medium-sized manufacturers to adopt deep technology stacks at a fraction of the cost of hiring external consultants.
 
Cobots are gaining in payload capacity and greater freedom of movement. Is the difference between them and conventional robots getting blurred?
Traditionally, cobots were designed for lower payload capacities compared to conventional robots. However, their payload capacities have steadily increased with advancements in cobot design and engineering. This increased payload capacity brings cobots closer to the capabilities of conventional robots. Cobots have also been evolving in terms of their range of motion. While earlier cobots were typically limited to simple linear movements or specific predefined paths, newer models feature more degrees of freedom, enabling them to perform more complex motions and reach a broader range of positions. This expanded range of motion allows cobots to carry out tasks that previously required conventional robots.
 
In addition, cobots are being equipped with increasingly sophisticated and specialised end-of-arm tools (EOATs) to enhance their capabilities. The availability of advanced EOATs allows cobots to perform tasks that were once exclusive to conventional robots. AI integration enhances cobots’ perception, decision-making, and interaction capabilities. This integration brings cobots closer to the level of sophistication exhibited by conventional robots.
 
R Vijayalayan manages the automotive industry and control design vertical application engineering teams at MathWorks India. He specialises in the field of Industrial Automation, Robotics and Model-Based Design.