Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):
Let us know if you have suggestions for next week, and enjoy today’s videos.
Nothing is more secure than a workplace protected by prowling robots. Nothing.
But are the fish okay?
[ Cobalt ]
ElliQ, a social home robot for seniors, has been in the works for a while. It looks good in this video, but remember, all robots look good in videos like these.
[ ElliQ ]
Zuzana from Quanser wrote in to share this video of their new Autonomous Vehicles Research Studio:
We recently launched this complete open-architecture, multi-vehicle lab, with Intel Aero Compute-powered QDrones, QBot ground robots, OptiTrack camera system, and our QUARC real-time rapid control prototyping software for Simulink. We developed it to help researchers in the autonomous robotics space start their work faster. Rather than spending time on developing and integrating DIY drones, coding, or other low-level tasks, they can start testing their controllers and strategies indoors within hours.
[ Quanser ]
Resources that future explorers could use to make rocket fuel, life support or building materials, are just below the surface of the Moon, Mars or other alien ground. Low-mass, high-performance and fully autonomous machines can bring these possibilities to the surface. Teams of college-level students from across the nation will put their excavator robots to the test during NASA’s 2018 Robotic Mining Competition. Catch the action May 16-18 at the Kennedy Space Center Visitor Complex.
[ NASA RMC ]
In an impendingly tiresome new world record, over 1,400 drones were airborne at the same time in China last weekend, making shapes and spelling words and stuff. The only reason we’re bothering to post about it is because something went wrong at the end, and drones started falling out of the sky:
It doesn’t look like anyone was hurt, but consider this a friendly reminder that drones of all shapes and sizes, carrying cameras or cargo or humans, can have bad days sometimes. And you don’t want to be under them (or in them) when they do.
Imagine a world… In which sending robots to Mars… Was made even more dramatic… Than you ever.
[ Insight ]
It feels like I harp on this every single year, but I wish that competitions like VEX (and FIRST) would put some more emphasis on robot autonomy. They could do that, for example, by providing more points and time for the autonomous portion of each run, and de-emphasizing the human remote control aspect. Robotics is becoming a software problem more than a hardware problem, and to be successful in the field long term, understanding autonomy is arguably more important than being able to build a robot. Programming an autonomous robot can be challenging, but kids are smart. They can handle it.
[ VEX ]
Prime Minister Justin Trudeau manages to restrain himself from running over photographers with a robot:
The robot in question was created by Erin Kennedy, and it’s designed to be a super accessible way for people participate in environmental cleanup. Read more at the link below.
[ Robot Missions ]
To help get development on Misty gain momentum, Misty Robotics has been holding hackathons (robothons?) out in Colorado:
And here’s an example of how Misty does its own mapping:
[ Misty Robotics ]
In search and rescue operations, every minute counts. When two Polish tourists found themselves stranded on the side of a mountain in Northern Iceland, and the 112 emergency service was unable to locate them by GPS, the Dalvik Search & Rescue Team knew they could count on DJI Phantom 4 to save the helpless hikers.
[ DJI ]
Starship robots are now delivering food, drinks, parcels and other items on corporate and academic campuses around the world. This new service allows staff the freedom to choose how and where to spend their time during the day.
Starship’s initiative is the first large scale deployment of autonomous delivery services, supporting campuses by implementing robots to assist in work and school environments. The robots offer on-demand delivery anywhere on participating campuses via an app, offering employees the flexibility and convenience of having food delivery when and where they want, eliminating unwanted errands and waiting in line, or transporting items to and from other locations on campus.
[ Starship ]
The more data you have to train autonomous cars with, the better your results are going to be, especially in situations that you weren’t expecting. Oxford Robotics Institute took some vehicles to Iceland to gather some serious off-road data, while testing out some rugged new sensors at the same time.
Middle Size robot soccer is one of my favorite events to watch, and Tech United is among the best. Here are four matches from the recent Portugese Open:
[ Tech United ]
Rafael Hostettler is talking about the Roboy project with its new Roboy 2.0 and the agile hardware development organization behind the products.
[ Roboy ]
In this week’s episode of Robots in Depth, Per interviews Andrew Graham from OC Robotics.
Andrew tells the story about starting OC Robotics as a way to ground his robotics development efforts in a customer need. He felt that making something useful gave a great direction to his projects. We also hear about some of the unique properties of snake arm robots: they can fit in any space that the tip of the robot can get through, they can operate in very tight locations as they are flexible all along and therefore do not sweep large areas to move, they are easy to seal up so that they don’t interact with the environment they operate in, and they are set up in two parts where the part exposed to the environment and to risk is the cheaper part. Andrew then shares some interesting insights from the many projects he has worked on, from fish processing and suit making to bomb disposal and servicing of nuclear power plants.
[ Robots in Depth ]
This week’s CMU RI Seminar comes from Vladlen Koltun, director of Intel’s Intelligent Systems Lab, on “Learning to Drive.” Robots learning to drive, we assume.
Why is our understanding of sensorimotor control behind our understanding of perception? I will talk about structural differences between perception and control, and how these differences can be mitigated to help advance sensorimotor control systems. Judicious use of simulation can play an important role and I will describe some simulation tools that we have built and deployed. Much of the talk will focus on autonomous driving as a compelling application domain for the study of coupled perception and control.
[ CMU RI Seminar ]