2D Is Against My Religion with Michal Gula
Jul 17, 2026 · 1 hr 31 min · 17 segments
Autonomous 3D scanning, GPS-denied SLAM, and Level 4B robotics are reshaping surveying, mining, and reality capture. **Exyn Technologies COO Ben Williams** explains the difference between automation…
Michal GulaHostSo when you think of automation, it is really something that is human defined, human scoped, human implemented, and then machine executed.
So think of something that is a highly repetitive process, but one that doesn't change much.
And in that case, that's like an assembly line or something that is very automated in the sense that it doesn't change.
The problem there is that if anything changes in the environment or modifications to the processor, something new has to happen, it still requires a human hand to intervene.
And then once it's been changed again and the human hand has finished all of its work, then the machine can take over and perform that repetitive process.
But out in the real world where you can't control the environment, you can't control all the variables, that gets really difficult to manage.
You either have to do a ton of pre-work and a ton of planning ahead of time to handle all the edge cases and that sort of thing, or you're sort of constantly restarting or changing the process, which is also a ton of work on the human side, versus an autonomous system takes on some of that resiliency and takes on some of that sort of human thought, the human hand, so to speak, where you're just defining a high-level mission objective and the system self-defines how it responds on a lower level.
And so it can respond to changes in the environment or changes in the specifics on the ground level where the human doesn't have to intervene necessarily.
So when you think of automation, it is really something that is human defined, human scoped, human implemented, and then machine executed.
So think of something that is a highly repetitive process, but one that doesn't change much.
And in that case, that's like an assembly line or something that is very automated in the sense that it doesn't change.
The problem there is that if anything changes in the environment or modifications to the processor, something new has to happen, it still requires a human hand to intervene.
And then once it's been changed again and the human hand has finished all of its work, then the machine can take over and perform that repetitive process.
But out in the real world where you can't control the environment, you can't control all the variables, that gets really difficult to manage.
You either have to do a ton of pre-work and a ton of planning ahead of time to handle all the edge cases and that sort of thing, or you're sort of constantly restarting or changing the process, which is also a ton of work on the human side, versus an autonomous system takes on some of that resiliency and takes on some of that sort of human thought, the human hand, so to speak, where you're just defining a high-level mission objective and the system self-defines how it responds on a lower level.
And so it can respond to changes in the environment or changes in the specifics on the ground level where the human doesn't have to intervene necessarily.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
