FEATURE Machine vision
Is LiDAR on its way out? Camera’s market size is growing
IDTechEx Technology Analyst Yulin Wang discusses the camera’s market for autonomous machines, which will grow by 3% to 79% within ten years
A
utonomous mobility is the key value proposition for many developers, thanks in large portion to the successes of self-
driving systems by companies like Tesla and John Deere.
Autonomous driving has gained
signifi cant momentum across the robotics industry. Although nothing new and traditionally mostly relying on LiDAR, this technology is going out of favour because of its limitations like high upfront costs, low resolution and lack of object recognition ability. More recently, Tesla and John Deere have both used autonomous vehicles based on cameras only, which now look set to take over this market. IDTechEx’s recent research “Sensors for Robotics 2023-2043: Technologies, Markets, and Forecasts” shows that the market share of LiDAR in the robotics industry will decrease from 24% to 21%, whereas the market share of cameras is expected to increase by 3% over the next decade.
LiDAR vs camera benefits One of the benefi ts of LiDAR is that it is less susceptible to poor weather conditions and limited visibility compared to cameras. Whilst this is a signifi cant benefi t for outdoor robots that work in unpredictable weather, it is not necessary for indoor mobile robots because they are fundamentally designed to work in a well-controlled environment with stable artifi cial illumination. In addition, unlike LiDAR, which provides a 3D point cloud, cameras can capture both 3D and colour information, allowing robots to recognise and diff erentiate objects around them. The 3D-information capturing ability paves the way for cameras to replace LiDAR. Then there are the high costs of LiDAR
hardware, which drive end users to look to alternative technologies. Cost is a major factor in the shift away from LiDAR. LiDAR sensors can be expensive, with prices ranging from a few hundred dollars to several thousand. In comparison, cameras are much more aff ordable, making them a more accessible option for many. This has resulted in the wider adoption of camera- based systems, since now they are more cost-
26 September 2023 | Automation
Sensors for robotics to year 2032, as per IDTechX analysis
eff ective for smaller companies and start-ups (which a lot of robot OEMs are). Nevertheless, despite the low costs of camera hardware (image sensors), the total cost of ownership can be extremely high for cameras because of the software and image processing units such as GPUs. We should also address the units’ size and weight. Cameras are smaller than LiDAR, making them easier to integrate into mobile robots. This allows for more compact and lightweight designs, which can be crucial for robots that need to navigate through tight spaces or narrow doorways. Additionally, cameras can be placed in multiple locations on the robot, providing a wider fi eld of view and improving its navigation accuracy. In addition to all these points, there’s the machine’s maintenance. Cameras are easier to calibrate and maintain compared to LiDAR. LiDAR requires careful alignment to ensure that the 3D point cloud is accurate, which can be diffi cult to maintain over time. On the other hand, cameras are typically plug and play, making them easier to use and maintain.
Snags However, despite all these camera advantages, there are also barriers holding back their adoption: The high costs of software and other image processing units are one example. Although image sensors are much cheaper than LiDAR, the total cost of ownership of cameras, along with the image processing units (software and GPUs),
can lead to a high total cost of up to several thousand dollars. Also, making cameras function robustly, a solid machine vision system is needed. Unlike Tesla and John Deere, many robot OEMs have limited cash fl ow, making them conservative in investing too much capital on developing machine- vision software. This draws them to existing LiDAR solutions. Then there’s data privacy: Many
warehouse owners are hesitant to use mobile robots with cameras into their warehouses due to data privacy concerns. The lack of interest from end users slows down the adoption of cameras in robots. Furthermore, the lack of images and data collected from warehouses due to data privacy also makes it harder for robot OEMs to develop a robust machine-vision system. Still, the shift toward camera- based systems for indoor mobile robots is a refl ection of the changing priorities in the fi eld. As costs come down and technology improves, cameras are becoming a more accessible and eff ective solution for indoor navigation and mapping. While LiDAR will likely still have a place in some applications and cameras present their own issues in the short term, it’s clear that cameras will become the dominant sensor for indoor mobile robots in the coming years.
CONTACT:
IDTechEx www.
idtechex.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 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50
