Listen to this article

Combining Machine Learning (ML) and 5G connectivity is a natural next step in the development of more autonomous robots. This, however, requires the availability of robust robotics development and execution platforms, along with robotics engineering expertise. But even as handful of large vendors are concentrating on the former (Qualcomm with the newly released RB6 platform, for example), the hiring and training new personnel, especially engineers, remains lackluster. A lack of additional robotics platform support, along with a limited pool of engineering talent, is likely stall actual advances in the robotics sector.

ML & 5G Coming to Your Robot
With the advent of 5G connectivity and Machine Learning (ML) processing on ever smaller devices, it was inevitable that robotics would eventually benefit from both. Thus, it is unsurprising that a major technology provider such as Qualcomm would release a platform for the purpose of making ML and 5G capabilities available to roboticists.

Qualcomm’s RB6 and More
Recently launched, Qualcomm’s RB6 platform, along with the RB5 AMR Reference Design, come with very ambitious goals – in a nutshell, to make autonomous mobile robots (AMRs) more, well, autonomous. Aimed at assisting developers create intelligent devices, where by ‘intelligent’ it is meant the possibility to carry out ML processes on the devices themselves, the RB6 Platform comes with a suite of advanced tools for this purpose, from 5G connectivity supporting global sub-6GHz and millimeter Wave bands to the edge ML and video processing capabilities supported by a Qualcomm AI Engine capable of carrying out 70-200 trillion operations per second.

The RB5 Reference Design, in turn, offers tightly integrated ML and 5G capabilities to bring it all in. An all-in-one solution, the RB6 Platform and RB5 Reference Design together provide the necessary hardware and software development tools to make robots smarter, faster, and safer for everyone.

Edge ML for Robotics
Such a set-up is obviously rather attractive, but there are also some significant shortcomings. On-device ML processes are typically of the inferential kind, as little to no training is conducted at the edge at present, and thus this will require the requisite training to be conducted on a server elsewhere, the result of such training then to be applied as an inference in whatever setting a robot is placed.

This introduces unavoidable delays and perhaps not as much autonomy as needed for certain applications – last-mile delivery is one of the targets of Qualcomm’s Platform and Reference Design combo, for instance – not to mention the resources required to conduct training-and-then-inference processes. On-device training is a distant goal at present, at least the more advanced processes, and while the possibility of applying inferences can clearly augment a robot’s capabilities, the real benefits will be reaped when a robot is capable of applying training models on data that itself has processed in situ.

5G Operational Environments
For robotics systems, 5G connectivity, while offering greater and higher bandwidth than 4G and WiFi networks, and thus a faster and wider connection overall, performs better in outdoor environments than indoors. This is especially true in the case of millimeter Wave bands, which have reduced range and penetrability compared to other cellular networks.

High-band 5G (that is, in frequencies between 24 and 47 GHz) is particularly an issue in manufacturing and warehouses environments, where the amount of shelving and metal can interfere with 5G signals. Since, therefore, this will require many more cells for a smooth functioning, this type of set-up may well affect its application in robotics, as in the already-mentioned last-mile delivery. A faster and broader network obviously offers great advantages, but the roll-out and implementation of 5G networks remains a goal to be attained, in industry and elsewhere.

Software-based tools for developing robotics systems, and this is what Qualcomm’s recently-launched products effectively are, are important, but more sophisticated development and research is still hampered by the shortage of robotics engineering expertise.

A Brighter Future
The robotics market is benefiting a great deal from endeavors such as Qualcomm’s RB6 solution, and you can expect faster, more comprehensive platforms and reference designs to be available to vendors in the near future. This also includes hardware accelerators of various kinds, agnosticism regarding operating systems and software more generally, and simply more collaboration in developing robotic tools more generally.

Engineering Expertise Challenge
This is where the market is headed, and some kind of integration of 5G connectivity, as well as of ML processes within robots, is the next natural step. However, it is also the case that these measures are, in a way, necessary patches over some of the very real deficiencies in the market. Indeed, in recent years there is a significant shortage of engineers in robotics and Artificial Intelligence, the latter broadly construed, and these recent developments constitute a reflection of the general state of affairs.

Software-based tools for developing robotics systems, and this is what Qualcomm’s recently-launched products effectively are, are important, but more sophisticated development and research is still hampered by the shortage of robotics engineering expertise. As such, these new tools are likely to offer a short-term solution rather and this ought to be of some concern, as in the long run there may be diminishing returns with this approach.

Multi-disciplinary Teams and Collaboration
ABI Research believes that for robotics systems development to accelerate and serve the needs of industry more adequately, there should be increasing investment in areas that require experts from different fields, especially those that are resource- and time-intensive, as is the case in robotics. Such investment would also benefit from deeper collaboration with public research centers and institutions.