TECHNOLOGY FOCUS Electrical & electronic systems


Ross Turnball says humanoid robotics can operate in manufacturing environments without compromising reliability or requiring major system redesign


across this chain introduces cumulative error in timing and motion accuracy. Signal conditioning and real-time processing


CUSTOM ASICs FOR HUMANOIDS


Here, Ross Turnbull, director of business development at Swindon Silicon Systems, explains how humanoid robotics is evolving and why ASICs are critical to reliable real-world performance


T


he BMW Group’s deployment of AI-enabled humanoid robots in automotive production highlights the shift towards physical AI


in manufacturing environments. These systems are designed to support repetitive high-precision tasks within factories where adaptability and consistency are important. The global robotics industry continues to expand as automation increasingly becomes embedded across automotive, electronics and logistics sectors. According to the International Federation of Robotics, “542,000 industrial robots were installed globally in 2024”, bringing the total number of operational units to 4.66 million. Within this broader market, humanoid


robotics remains an emerging segment, with Goldman Sachs projecting the sector to reach around USD 38 billion by 2035 as development moves from pilot systems towards industrial deployment. Humanoid robots are robotic systems designed with human-like form factors that allow operation in environments built for people. Unlike traditional industrial robots, which are fixed to specific tasks and locations, humanoids are designed for adaptability in dynamic environments where workflows are not fully structured.


In manufacturing settings, these systems are


used for repetitive assembly, material handling, inspection and support tasks. Deployments in automotive production demonstrate this shift, with humanoid platforms operating alongside human workers to support precision- driven tasks while improving production flexibility without major changes to existing infrastructure. Physical AI combines digital intelligence with physical systems that perceive, decide and act within real-world environments.


28 May 2026 | Automation


Performance depends on how effectively computational output is translated into physical execution. Humanoid robots process large volumes of sensor data in real time while maintaining precise motion control. This introduces constraints including signal noise, latency, mechanical variation and environmental interference. Even small reductions in signal integrity directly impact stability and accuracy in repetitive operations.


AI defines decision making, but execution depends on the quality of underlying electronics. Industrial environments introduce vibration, electrical noise and temperature variation, which affect signal quality and system response.


As humanoid systems move from pilot deployment to continuous operation, these constraints significantly increase. Performance must remain consistent across thousands of cycles under variable conditions without degradation in precision or control stability. Humanoid operation depends on the interaction between sensing, processing and actuation. Sensors capture environmental data, processing systems interpret it and control systems execute movement. Any disruption


therefore define system stability. Latency and noise become direct limiting factors in whether performance can be sustained at scale. Application specific integrated circuits (ASICs) integrate sensing, processing and control functions into silicon designed for specific applications. Unlike general purpose components, ASICs are optimised for efficiency, consistency and deterministic operation.


In humanoid robotics, this enables signal conditioning and processing at hardware level, reducing the distance between data capture and execution. This improves responsiveness, stabilises motion control and increases accuracy in repetitive tasks where consistency is critical.


ASIC integration reduces system complexity by consolidating functions into a single device. This lowers component count and reduces potential failure points while simplifying overall system architecture in continuous industrial operation. ASICs deliver improved signal integrity,


reduced noise sensitivity, lower latency and higher energy efficiency compared with general purpose solutions. These characteristics support continuous operation in variable industrial environments where stability is required.


System-level integration reduces design complexity and improves long-term reliability by limiting dependency on multiple discrete components subject to supply variation or obsolescence. In industrial applications, where lifecycles extend beyond 15 to 20 years, this stability becomes a critical factor. Scalability depends on consistent performance across diverse operational environments. Tightly integrated electronic systems are therefore required to maintain predictable behaviour under real-world constraints.


ASIC-based architectures provide a foundation for scalable deployment by enabling consistent performance across systems while reducing integration overhead.


Swindon Silicon Systems www.swindonsilicon.com


automationmagazine.co.uk


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40