Video Friday: Innfos Humanoid Robot, and More

Your weekly selection of awesome robot videos

5 min read

Evan Ackerman is IEEE Spectrum’s robotics editor.

Erico Guizzo is IEEE Spectrum's Digital Innovation Director.

Innfos HR-1 Humanoid Robot
Image: Innfos via YouTube

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!):

HRI 2019 – March 11-14, 2019 – Daegu, Korea
RoboSoft 2019 – April 14-18, 2019 – Daegu, Korea
Nîmes Robotics Festival – May 17-19, 2019 – Nîmes, France
ICRA 2019 – May 20-24, 2019 – Montreal, Canada
2nd Annual Robotics Summit & Expo – June 4-6, 2019 – Boston, Mass., USA
Energy Drone Coalition Summit – June 12-13, 2019 – Woodlands, Texas, USA

Let us know if you have suggestions for next week, and enjoy today’s videos.

We’re used to seeing bipedal robots keep their balance by continuously stepping in place, but not that many are competent enough to learn how to balance, walk, and go back to balancing again, like humans do, let alone climb stairs.

Cassie is learning fast. Very fast.

[ Agility Robotics ]

A Chinese company called Innfos is introducing a “high-performance humanoid robot.” We know almost nothing about it, except that it features “highly integrated smart compliant actuators.”

It’s not clear how much of this is autonomous, and note that some of the footage has been sped up, but some of its performance is impressive and we’re looking forward to learning more about it.

[ Innfos ]

Advances in construction automation have primarily focused on creating heavy machines to accomplish repetitive tasks. While this approach is valuable in an assembly-line context, it does not always translate well for the diverse terrain and dynamic nature of construction sites. As a result, the use of automation in the architectural assembly has lagged far behind other industries. To address the challenges of construction-site assembly, this project suggests an alternative technique that uses a fleet of smaller robots working in parallel.

In our tests, we used a team of small mobile robots to fold 2D laser-cut stock into 3D curved structures, and then assemble these units into larger interlocked forms.

The proposed method, which is inspired by the construction techniques of insect colonies, has several advantages over the use of larger machines. It allows for much greater on-site flexibility and portability. It is also easy to scale the operation, by adding or removing additional units as needed. The use of multiple small robots provides operational redundancy that can adapt to the loss of any particular machine. These advantages make the technology particularly suitable for construction in hazardous or inaccessible areas. The use of assembly robots also opens new horizons for design creativity, allowing architects to explore new ideas that would be unwieldy and expensive to construct using traditional techniques.

[ Aaron Becker ]

Panasonic’s got a new square-ish mopping robot called Rollan:

It sounds like you’re supposed to vacuum first, and then run this little guy to give the floor a nice wash. As Panasonic’s Google-translated Rollan site says, “Japanese life close to the floor. Why do not you add a floor cleaning to the finish after the usual vacuum cleaner?”

[ Panasonic ]

Watch Sidd Srinivasa answer all the questions about robots that we really want to ask him but feel like we’re too old to.

Oh man, that was brutal at the end there. Poor Kuri.

[ UW ]

A brief example of what programming a new custom skill on what Misty looks like.

[ Misty Robotics ]

This is a RoboCup Small Size video from a couple years back, but it’s worth watching because of the sick curveballs that these little bots can kick. And it’s more than a novelty- if you watch until the end, you’ll see it happen in a real RoboCup game.

[ YouTube ]

Robotstart visited HCJ2019, “Japan’s Largest Exhibition for Hospitality, Food Service, and Catering,” which had an assortment of cute food prep robots. I have to warn you, though, that it looks as though hot things weren’t allowed on the show floor, so the poor robot trying to make toast and an omelette ends up just making a little bit of a mess.

[ Robotstart ]

Shoe boxes are its specialty: the intelligent picking robot TORU can handle individual boxes and can transport a backpack full of them directly to a handover station. In case of storage or returns? Back they go.

TORU can be profitably integrated into many processes – such as storage, picking, relocation and consolidation of the warehouse. From navigation through to the transfer of objects picked with pinpoint accuracy, it carries out transport orders autonomously. Thanks to its capabilities and intelligent software, it can be easily and quickly configured and flexibly adapted to new structures.

[ Magazino ]

When a volcano erupts, molten rocks, ash, pyroclastic flow, and debris flow can cause disasters. Debris flow is responsible for enormous damage across large areas. This makes debris flow simulations a crucial means of determining whether to issue an evacuation warning for area residents. For safety purposes, restricted areas are designated around volcanos during eruptions, making it difficult to gather information (such as the amount and permeability of ash) required for precise debris flow simulations. An unmanned observation system, intended for use in such restricted areas, was developed to address this issue.

The proposed system is based on a multirotor micro-unmanned aerial vehicle (MUAV) that transports cameras, small devices to measure target environments, and a small robot to active volcanic areas. Field experiments were conducted at Mt. Asama and Mt. Unzen-Fugen to validate the function of the system. Data obtained by these systems can contribute to the improvement of debris flow simulations developed in the project.

[ Tohoku University ]

At some point, a very large delivery drone just becomes a very small helicopter, right?

[ Drone Delivery Canada ]

We don’t hear much about Kazakhstan robotics, but they’ve got plenty going on—here’s a RoboCon competition from just last week.

[ RoboCon ]

SWARM Logistics Assistant comes up from H2020 CPSwarm project. In it, Robotnik contributes with its knowledge in Cyber Phisical Systems. Robotnik has large experience in ROS, software used by all their robots, furthermore in the simulation software. The project has several mobile platforms from Robotnik, which are working to supporting the workers in tedious tasks in a warehouse.

[ Robotnik ]

The video was realized in collaboration with expert surgeons of the ICAROS center with the da Vinci Research Kit (DVRK) robot equipped with an open controller. A preliminary application of a novel force sensor integrated into the trocar is shown. This innovative solution permits the external force estimation without any modification of the surgical laparoscopic instruments. The force estimation will overcome the lack of surgeons’ force perception when operating with the da Vinci robot that can produce: tissues damages, reduced perception of the suturing thread traction and impossibility to make diagnosis in loco.

[ PRISMA Lab ]


This video shows Waymo’s self-driving car approaching a traffic light that is not working. The car comes to a stop before entering the intersection and waits for the officer signal that we can proceed.

[ Waymo ]

Friend of the blog and robotics professor Angelica Lim speaks with Stacey Mulcahy at Microsoft about, you know, robot stuff.

[ ROSIE Lab ] via [ Microsoft Vancouver ]

Oliver Cameron is the Co-Founder and CEO of Voyage. Before that he was the lead of the Udacity Self-Driving Car program that made ideas in autonomous vehicle research and development accessible to the world.

[ MIT ]

This week’s CMU RI Seminar is by Jeff Schneider from Uber ATR on “Self-Driving Cars and AI.”

Artificial intelligence and machine learning are critical to reaching full autonomy in self driving cars. I will present two autonomy systems along with the use of machine learning in each of them. I will summarize recent progress in commercializing these systems and make some observations about the potential impact of these systems in our daily life. Some of the biggest remaining challenges include efficiently solving the long tail of unusual events on the road, scaling up from demos to commercially viable systems, and verifying the safety of these AI-based systems. I will finish with thoughts on addressing those issues.

[ CMU RI ]

The Conversation (0)