Humanoid robots are transitioning from conceptual prototypes to AI-driven machines suited for early rollout in commercial and industrial environments. A major component of this transition is the array of sensors integrated into each robot. A new report by IDTechEx, ‘Sensors for Humanoid Robots 2027–2037: Technologies, Players, Forecasts’, forecasts that the market for sensors in humanoid robots could reach $6,59 billion by 2037, representing a compound annual growth rate of 21,4%.
Commercial humanoid robot models differ considerably in the exact sensor arrays used, but there are generally five core categories: perception sensors, force/torque sensors, encoders, inertial measurement units, and tactile sensors. These sensors provide information about the robot’s internal state and external environment, with data from multiple sensor types combined and processed through sensor fusion to allow the robot to make decisions about its next actions and operate with multiple layers of safety mechanisms.
Perception sensors and the intersection with automotive autonomy
Perception sensors are a key differentiator between humanoid robot models. The IDTechEx report covers depth cameras, lidar, ultrasonic sensors and mmW radar. There is ongoing debate in the current market as to whether cameras alone are sufficient for navigation and mapping, or whether lidar is needed for its depth-sensing capability and robustness to changing lighting conditions. The advantages and limitations of each sensing technology are examined in the report, alongside case studies of robot designs using lidar and cameras versus the camera-only route.
There is significant overlap between the sensors used for humanoid robots and those developed for advanced driver assistance systems and autonomous vehicles. Both have similar requirements, dynamically sensing and predicting their environment, to make safe and effective decisions. Similar technologies and suppliers serve both industries, including Sony, Hesai Technology, Livox and Ouster.
The intersection is further complicated by the fact that many automotive companies are also developers of humanoid robots. They are significant investors in humanoid companies and often the first customers for commercial trials. Tesla develops its Optimus humanoid robot while also being a high-profile proponent of humanoids in automotive manufacturing, with both the robot and its autonomous vehicles using a camera-only approach to vision sensing and mapping.
Sensors for movement, balance and a delicate touch
Every humanoid robot design relies on actuators for movement, with the number of degrees of freedom varying by model. The joints and actuators require a combination of force sensors, torque sensors and encoders to operate efficiently. Force and torque sensors provide information about internal strains as well as external loads and forces from payloads or impacts.
Six-axis force/torque sensors, which measure linear forces and rotational torques in all three dimensions, are typically deployed in the ankles to enhance balance and in the wrists to enable precise object manipulation. These sensors are currently among the most expensive sensing components for a humanoid robot, partly because of limited supply chain overlap with industries outside robotics. Most other applications use them as precision instruments in relatively low annual volumes compared with what future humanoid deployments will require.
Tactile sensing covers a wide range of technologies with MEMS, capacitive, printed/flexible, optical, and magnetic sensors all under investigation. Tactile sensors can be deployed in the hands or grippers of humanoid robots, or more broadly in electronic skins covering larger portions of the body. This makes tactile sensing an area of active innovation, and a key differentiator between different models and manufacturers.
Market outlook
Humanoid robots must be equipped with a variety of sensors to plan and execute tasks, operate safely around other robots and people, and navigate dynamic real-world environments. A sustainable commercial rollout will depend on a sensor manufacturer ecosystem able to scale with humanoid adoption without creating critical supply chain bottlenecks. The IDTechEx report examines which sensor types are being deployed in humanoid models aimed at high-volume commercial use, where they are manufactured and by whom, and where future trends, potential bottlenecks or disruptive innovations may emerge.
For more information contact IDTechEx,
© Technews Publishing (Pty) Ltd | All Rights Reserved
printer friendly version