There’s a story that goes back to the 1980s or so about an engineering professor who laid down a challenge to the students of his automation class: design a robot to perform the most mundane of household tasks — washing the dishes. The students divided up into groups, batted ideas around, and presented their designs. Every group came up with something impressive, all variations on a theme with cameras and sensors and articulated arms to move the plates around. The professor watched the presentations respectfully, and when they were done he got up and said, “Nice work. But didn’t any of you idiots realize you can buy a robot that does dishes for $300 from any Sears in the country?”
The story may be apocryphal, but it’s certainly plausible, and it’s definitely instructive. The cultural impression of robotics as a field has a lot of ballast on it, thanks to decades of training that leads us to believe that robots will always be at least partially anthropomorphic. At first it was science fiction giving us Robbie the Robot and C3PO; now that we’re living in the future, Boston Dynamics and the like are doing their best to give us an updated view of what robots must be.
But all this training to expect bots built in the image of humans or animals only covers a narrow range of use cases, and leaves behind the hundreds or thousands of other applications that could prove just as interesting. One use case that appears to be coming to market hearkens back to that professor’s dishwashing throwdown, and if manufacturers have their way, robotic dishwashers might well be a thing in the near future.
Harvesting delicate fruit and vegetables with robots is hard, and increasingly us humans no longer want to do these jobs. The pressure to find engineering solutions is intense and more and more machines of different shapes and sizes have recently been emerging in an attempt to alleviate the problem. Additionally, each crop is often quite different from one another and so, for example, a strawberry picking machine can not be used for harvesting lettuce.
The machine uses YOLO3 detection and classification networks to get localisation coordinates of the crop and then check if it’s ready for harvest, or diseased. A standard UR10 robotic arm then positions the harvesting mechanism over the lettuce, getting force feedback through the arm joints to detect when it hits the ground. A pneumatically actuated cutting blade then attempts to cut the lettuce at exactly the right height below the lettuce head in order to satisfy the very exacting requirements of the supermarkets.
Rather strangely, the main control hardware is just a standard laptop which handles 2 consumer grade USB cameras with overall combined detection and classification speeds of about 0.212 seconds. The software is ROS (Robot Operating System) with custom nodes written in Python by members of the team.
Although the machine is slow and under-powered, we were very impressed with the fact that it seemed to work quite well. This particular project has been ongoing for several years now and the machine rebuilt 16 times! These types of machines are currently (2019) very much in their infancy and we can expect to see many more attempts at cracking these difficult engineering tasks in the next few years.
The build is a small, radio-controlled FPV trike. Instead of the usual skid-steer setup, the rear wheel is mounted on a pair of horizontal bearings which allows it to pivot left and right. A servo is used to control the rear wheel position, with a pair of tie rod ends used to connect the horn to the rear steering assembly. It’s not the only unconventional design choice, either – magnets are used to affix the top plate to the vehicle chassis, rather than screws or clips. For video, the user can mount either a small dedicated FPV camera, or a GoPro with the included mount.
Without any code or control details posted, we can’t be 100% sure how it all works. However, from the video, it appears that both front wheels are being driven at the same speed, with steering handled solely by the rear wheel. This is apparent when driving on a smooth surface, where the vehicle can be seen to slide when turning. While it’s unlikely this setup has many advantages over a simpler differential steering build with a caster, it does show that rear steering can be effective on its own.
Take a dozen or so fish hooks, progressively embed them in plastic with a 3D printer and attach them to the feet of your hexapod and you’ve got a giant cockroach!
A team of researchers at Carnagie Mellon University came up with this ingenious hack which can easily be copied by anybody with a hexpod and a 3D printer. Here you can see the hooks embedded into the ends of a leg. This ‘Microspine technology’ enables their T-RHex robot to climb up walls at a slightly under-whelming 55 degrees, but also grants the ability to cling on severe overhangs.
Our interpretation of these results is that the robot needs to release and place each foot in a much more controlled manner to stop it from falling backwards. But researchers do have plans to help improve on that behavior in the near future.
Sensing and Closed Loop Control: As of now, T-RHex moves with an entirely open-loop, scripted gait. We believe that performance can be improved by adding torque sensing to the leg and tail actuators, which would allow the robot to adapt to large-scale surface irregularities in the wall, detect leg slip before catastrophic detachment,and automatically use the tail to balance during wall climbs.This design path would require a platform overhaul, but offers a promising controls-based solution to the shortcomings of our gait design.
No doubt we will all now want to build cockroaches that will out perform the T-RHex. Embedding fish hooks into plastic is done one at a time. During fabrication, the printer is stopped and a hook is carefully laid down by human hand. The printer is turned on once again and another layer of plastic laid down to fully encapsulate the hook. Repeat again and again!
Your robot would need the aforementioned sensing and closed loop control and also the ‘normal’ array of sensors and cameras to enable autonomy with the ability to assess the terrain ahead. Good luck, and don’t forget to post about your projects (check out Hackaday.io if you need somewhere to do this) and tip us off about it! We’ve seen plenty of, sometimes terrifying, hexapod projects, but watch out that the project budget does not get totally out of control (more to be said about this in the future).
The last decade or so has seen remarkable advances in motor technology for robotics and hobby applications. We’re no longer stuck with crappy brushed motors, and now we have fancy (and cheap!) stepper motors, brushless motors for drones, and servo motors. This has led to some incredible achievements; drones are only barely possible with brushed motors, and you can’t build a robot without encoders.
For his entry into the Hackaday Prize, [Gabrael Levine] is taking on one of the hardest robotics challenges around: the bipedal robot. It’s a chickenwalker, or an AT-ST; either way, you need a lot of power in a very small space, and that’s where the OpenTorque Actuator comes in. It’s a quasi-direct-drive motor that was originally pioneered by the MIT Biomimetics Lab.
The key feature of the OpenTorque Actuator is using a big brushless motor, a rotation encoder, and a small, 8:1 planetary gear set. This allows the motor to be backdrivable, capable of force-sensing and open-loop control, and because this actuator is 3D printed, it’s really cheap to produce.
But a motor without a chassis is nothing, and that’s where the Blackbird Bipedal Robot comes in. In keeping with best practices of robotic design, the kinematics are first being tested in simulation, with the mechanical build happening in parallel. That means there’s some great videos of this chickenwalker strutting around (available below), and so far, everything looks great. This bipedal robot can turn, walk, yaw, and work is continuing on the efforts to get this bird-legged bot to stand still.
Building robots can be fun, and remains a popular pastime among many in the hacker and maker set. However the hardware side of things can be daunting. This is particularly the case for those attempting to build something on a larger scale. A great shortcut is to start with a robust mechanical platform from the outset – and using an electric wheelchair is a great way to do so.
[Nikita] started this project way back in 2009, after finding a broken electric wheelchair at a flea market. It was no longer in fit condition for use as a wheelchair, so [Nikita] was able to score it for the low price of just $50. That’s a great price for a package which includes a robust chassis, wheels, motors and the required controllers to drive it all. With the platform in hand, it was time to get hacking.
Thus far, [Nikita] has gone so far as to strip the wheelchair of all extraneous parts, leaving it as a motorized carriage. Radio control has been implemented with the help of an Arduino, and a couple of “eyes” have been added to give it a little personality. It can also still be driven with the original joystick, which has been relocated on the chassis. Future plans involve adding a level of autonomy to allow the ‘bot to navigate waypoints and recognise faces, both tasks which should be significantly easier with 2019 technology. We’re eager to see where it goes next; we’ve seen great applications of wheelchair hardware before, after all. Video after the break.
Wiping a whiteboard can be a tedious chore. Nobody wants to stick around after a long meeting to clean up, and sensitive information is often left broadcast out in the open. Never fear, though – this robot is here to help.
Wipy, as the little device is known, is a robotic cleaner that scoots around to keep whiteboards clear and ready for work. With brains courtesy of an Arduino Uno, it uses an IR line-following sensor to target areas to wipe, rather then wasting time wiping areas that are already clean. It’s also fitted with a time-of-flight sensor for ranging, allowing it to avoid obstacles, or busy humans that are writing on the board.
If Wipy lacks anything, it’s probably discretion. Despite its cute emoji-like face, it’s not really capable of tact, or knowing when it’s not needed. It’s recommended to keep Wipy powered down until you’re completely finished, lest it barge in and start wiping off important calculations before you’re done.