Quadcopter Drone does Air, Water, Over and Under, Even Hitches a ride.

 Expecting  many more updates in drone autonomy, flexibility

A quadcopter that works in the air and underwater and also has a suction cup for hitching a ride on a host   by Bob Yirka , in TechXplore

A team of researchers at Beihang University, working with colleagues at Imperial College London and Swiss Federal Laboratories for Materials Science and Technology, has developed a quadcopter drone that is capable of flying in the air and maneuvering underwater. It also has a suction cup for hitching a ride on a host. They describe their drone in the journal Science Robotics.

Over the past several years, quadcopters have become a consumer product. And while the technology behind them is quite impressive, one drawback is their inability to survive a water landing. In this new effort, the researchers have not only overcome that problem, but they have also given their robot the ability to maneuver underwater and to hitch itself to undersea creatures.

Noting that quadcopters can still only fly for short periods of time, the researchers looked into the feasibility of a drone that could hitch a ride, similar to the remora fish. Remoras have a suction disc that allows them to attach to other fish, sharks and whales, thus conserving energy. To that end, the researchers created a suction disc modeled after the one sported by the remora.  ..... 

Hovermap for liDAR Innovation

Mapping with Lidar

LiDAR News by Gene Roe   

February 8, 2022 Leave a comment

Hovermap Wins Geo Week’s LiDAR Leader Outstanding Innovation Award

Emesent is proud to have their Hovermap LiDAR mapping and autonomy payload announced as the winner of the Geo Week LiDAR Leader Award for Outstanding Innovation.

“We’re honored to be recognized as an innovative leader in geospatial LiDAR technology,” said Dr Stefan Hrabar, Emesent CEO and Co-Founder.

Announced at the Geo Week Conference in Denver today (February 7, 2022), the LiDAR Leader Awards honor the achievements of individuals and teams working in the geospatial technology space. The Outstanding Innovation in LiDAR Award highlights excellence in innovations in this space.

“Having first launched Hovermap at Geo Week in 2019, our team is extremely proud to be acknowledged for the advances we’ve made in LiDAR-based SLAM mapping and autonomy since the launch. It’s been amazing to see the value our customers have enjoyed from scanning hazardous, GPS-denied environments that were previously inaccessible,” said Dr Hrabar.

Hovermap’s high quality, high resolution, colorized point clouds have enabled customers to derive new insights in mining, architecture, construction, engineering, forestry, and other verticals.

Hovermap was recognized for its advanced autonomy and mapping capabilities. When mounted on a drone, it provides safe, autonomous, beyond line of sight flight in challenging areas even without GPS.

Another key feature considered was Hovermap’s versatility. The plug and play capability allows users to easily detach it from a drone to perform walking, vehicle-mounted, or ground robot- based scans. This allows mapping practically any indoor or outdoor area quickly and easily. .... ' 

EU Proposed Definition of AI Problematic?

Seems a strange definition, covering much more than AI,  like analytics of most any kind,  just not autonomous?   I am concerned that this will regulated us out of many reasonable uses.

Europe Is in Danger of Using the Wrong Definition of AI   By Wired, March 7, 2022

The European Union's (EU) forthcoming Artificial Intelligence Regulation, also known as the AIA, will determine what artificial intelligence (AI) can be deployed in the EU, and how much it costs an organization to do so. The current draft starts with a broad definition of AI: “software that...can...generate outputs such as content, predictions, recommendations, or decisions influencing the environments they interact with.”

However, this definition may already be too narrow, given what the AIA is primarily about: ensuring that decisions made by or with machines are done so well, transparently, and with clear human accountability, at least if those decisions matter. ... 

For writing laws about AI, let's be broad and inclusive enough to help us keep our devices and systems safe for our societies ... 

From Wired  

McKinsey On Autonomous Plants

The autonomous plant: Entering a new digital era  

September 10, 2021 | Article  McKinsey

By Gopal Chakrabarti, Dominik Don, Micah Smith, and Premal Vora

The autonomous plant: Entering a new digital era

The requirements of the energy transition present significant industry challenges. Energy companies must embrace new technologies, transform management systems, and expand workforce capabilities.

Energy companies are operating in uncertain times. They face societal pressure and increased regulation to significantly reduce fossil-fuel dependency, primarily characterized by reliance on transport fuels, plastics, and other refining and petrochemical products. Under these conditions, companies are looking to maximize the health and resilience of downstream operations—particularly in oil and gas and chemicals—by adopting new automation and digital technologies, enabling increased levels of data usage and performance transparency, as well as faster decision loops.

Many of these changes were already occurring and have only accelerated during the COVID-19 pandemic, resulting in a newfound sense of urgency. Yet digital strategies remain challenging for the energy sector for several reasons, namely keeping up with increased decarbonization efforts, workforce changes, and accelerated technological innovations. Many companies have responded with short-term solutions but remain indecisive about how to identify priorities in the years to come.  ... ' 

Autonomous Drone Swarms

 A favorite topic, where we proposed swarms of drones to work together tracking warehouse conditions.

Autonomous Drone Swarm Can Localize Gas Leaks   By TU Delft (Netherlands)

Scientists at the Netherlands' Delft University of Technology (TU Delft), Spain's University of Barcelona, and Harvard University have engineered a swarm of tiny drones capable of autonomously detecting and localizing gas sources in cramped indoor settings.   Well before any autonomy was possible.

TU Delft's Guido de Croon said, "The drones' tiny size makes them very safe to any humans and property still in the building, while their flying capability will allow them to eventually search for the source in three dimensions."

The team implemented bio-inspired navigation and search methods to localize sources while using extremely limited onboard sensing and processing capabilities.

The drones deploy Snuff Bug, a navigation algorithm that lets the swarm spread out until a drone detects gas and alerts the others. Each drone will then collaborate to localize the gas source using a particle swarm optimization algorithm.

From TU Delft (Netherlands)

View Full Article  

U.S. Army Looks to Improve Quadrotor Drone Performance

Changes in flight capabilities for in context dynamic needs. 

U.S. Army Research Laboratory

December 8, 2020

The U.S. Army Combat Capabilities Development Command's Army Research Laboratory (ARL) and Rensselaer Polytechnic Institute researchers have developed a trajectory planner to speed the switch between hovering and forward flight in vertical takeoff and landing tail-sitter drones. The planner was engineered for the Army's Common Research Configuration (CRC) platform, a quadrotor biplane tail-sitter used in testing new design features and examining fundamental aerodynamics. The research team thinks the planner may eventually enable the CRC to intelligently switch between hover and forward flight while navigating across dense or urban areas. Said ARL’s Jean-Paul Reddinger, "This method ... is a step in the direction of integrating high-level autonomy with platform-specific dynamics."

California Says GM Can Test Fully Driverless Cars

This trend seems to be moving forward faster than expected.  Would expect these developments to push reliance in other autonomy efforts.

CA Says General Motors Can Test Fully Driverless Cars on Its Roads  in ACM By Futurism.com

The California Department of Motor Vehicles has granted permission to General Motors' self-driving car venture to test its autonomous cars without anyone in the driver's seat on the streets of San Francisco.

The California Department of Motor Vehicles (DMV) just granted permission to Cruise, General Motors' self-driving car venture, to test out its autonomous cars without anyone in the driver's seat.

California has given out permits that allow driverless tests with someone behind the wheel to 60 companies, The Verge reports. But Cruise is just the fifth to be permitted to test out cars that are completely empty. With the permit in hand, Cruise hopes to be the first to test a fully-driverless car on the streets of San Francisco.

Cruise's fleet, which has never been tested in public, The Verge reports, is made up of 200 electric Chevy Bolts. So essentially Cruise is trying to nail electric and autonomous cars all in one fell swoop. ....  "

AI and the Curious Consideration of Autonomous Intent

Context, Autonomy Intent... for Autonomous AI.  Considerable piece on the difficult problem.  Has not come close to technical solution.

Home  AI Trends Insider on Autonomy  On Whether AI Can Form ‘Intent’ Including In The Case Of Autonomous...

On Whether AI Can Form ‘Intent’ Including In The Case Of Autonomous Cars
By Lance Eliot, the AI Trends Insider

These remarks all have something in common:

The devil made me do it
I didn’t mean to be mean to you
Something just came over me
I wanted to do it
You got what was coming to you
My motives were pure
What’s that all about?

You could say that those are all various ways in which someone might express their intent or intentions.

In some instances, the person is seemingly expressing their intent directly, while in other cases they appear to be avoiding being pinned down on their intentions and are trying to toss the intent onto the shoulders of someone or something else.

When we express our intent, there is no particular reason to necessarily believe that it is true per se.

A person can tell you their intentions and yet be lying through their teeth.

Or, a person can offer their intentions and genuinely believe that they are forthcoming in their indication, and yet it might be entirely fabricated and concocted as a kind of rationalization after-the-fact.  ... " 

The Future will be More Autonomous, Humans will be Involved.

True, its been going that way for a long time ,  but has it really sped up greatly at the macro level?    At the level of 'self driving', 'identifying', 'charging' ....where people are integrated with larger context systems we are part of ?    We still have to be part of many systems in mundane ways.   Those systems have gotten very, very complex,  and  once they interact with humans, they slow down.   And because systems have been shown to be biased at times,  some would say we need to include humans.   I assume to be fairer, or at least to have someone to blame, or sue.

Good piece, which at the link below starts with RPA methods.

The future is autonomous: 5 reasons why automation will be tech’s major story in 2020

By Mark Albertson in SiliconAngle

This article wasn’t written by a robot, but it could have been. That, along with literally thousands of other uses, is why automation will be big news in 2020.

Over the course of 2019, it was nearly impossible to cover any major tech conference without discussing an innovation in robotics, artificial intelligence or a similar automation solution. Not every automated advance will be a surefire winner, but the body of evidence offers a convincing case that the field is moving rapidly and adoption will only continue to grow.  ....  "

Need to Understand Human Behavior Better for Car Autonomy

The word 'psychoanalyze' may be overstating it, but we need to know humans likely behavior in specific and often complex context.    As we now drive we do that all the time.   Can autonomous vehicles do it as well?   With the goal being progress and safety?

MIT is teaching self-driving cars how to psychoanalyze humans on the road    By Luke Dormeh  in Digitaltrends

In March 2004, the U.S. Defense Advanced Research Projects Agency (DARPA) organized a special Grand Challenge event to test out the promise — or lack thereof — of current-generation self-driving cars. Entrants from the world’s top A.I. labs competed for a $1 million prize; their custom-built vehicles trying their best to autonomously navigate a 142-mile route through California’s Mojave Desert. It didn’t go well. The “winning” team managed to travel just 7.4 miles in several hours before shuddering to a halt. And catching fire.

A decade-and-a-half, a whole lot has changed. Self-driving cars have successfully driven hundreds of thousands of miles on actual roads. It’s non-controversial to say that humans will almost certainly be safer in a car driven by a robot than they are in one driven by a human. However, while there will eventually be a tipping point when every car on the road is autonomous, there’s also going to be a messy intermediary phase when self-driving cars will have to share the road with human-driven cars. You know who the problem parties are likely to be in this scenario? That’s right: the fleshy, unpredictable, sometimes-cautious, sometimes-prone-to-road-rage humans. .... " 

Gaming in Autonomous Vehicles

Further distraction, but if you 'solve' the safety of autonomy, and people are no long in control,  then why not.   The term 'driver' starts to lose its definition, all passengers could become participants.  And if we choose proximity, or other definitions of possible invitation of participation?  Is that different than any other kind of game participation?   AR/VR can also come into play.  Intrigued by the idea, but still awaiting the safety solution.

Researchers bring gaming to autonomous vehicles    by University of Waterloo in TechExplore.

Researchers have designed multiplayer games occupants of autonomous vehicles can play with other players in nearby self-driving cars.

A new study, led by researchers from the University of Waterloo details three games created for level three and higher semi-autonomous vehicles. The researchers also made suggestions for many exciting types of in-car games for future exploration.

Level three and higher semi-autonomous vehicles are those that have, at minimum, environmental detection capabilities and can make informed decisions for themselves.

"As autonomous vehicles start to replace conventional vehicles, occupants will have much more free time than they used to," said Matthew Lakier, a Ph.D. student in Waterloo's School of Computer Science. "You could use time spent in commute to read a book, watch a movie, get ahead on work, or browse the internet. Still, not everything you do has to be all isolated.  .... "

Learning from Mistakes

Ultimately most important.  How do we learn from mistakes, and the contexts that created those mistakes?  A form of causal reasoning that we found most useful in our efforts.    A form of maintenance to0 that could be fed back into a loop for updating data based training.

Worker Robots that Learn from Mistakes
By University of Leeds (U.K.)

A robot arm attempts to clear a cluttered table.
University of Leeds scientists are using automated planning and reinforcement learning to train a robot to find an object in a cluttered space and move it.

Computer scientists at the University of Leeds in the U.K. are using the artificial intelligence techniques of automated planning and reinforcement learning to train a robot to find an object in a cluttered space and move it.

The goal is to develop robotic autonomy, a state in which the machine can assess the unique circumstances presented in a task and find a solution.

The main challenge is that in a confined area, a robotic arm may not be able to grasp an object from above, and instead must plan a sequence of moves to reach the target object in a way that allows it to grasp the object.

Said Leeds researcher Wissam Bejjani, "Our work is significant because it combines planning with reinforcement learning. A lot of research to try and develop this technology focuses on just one of those approaches."..... '

From University of Leeds (U.K.)