Left Menu
Development News Edition

Novel technique allows robots to play teammates t0 soldiers

Scientists have developed a new technique that allows robots to autonomously navigate in different environments and carry out actions a soldier would expect from a team mate on the battlefield.

Scientists have developed a new technique that allows robots to autonomously navigate in different environments and carry out actions a soldier would expect from a team mate on the battlefield.

The technique, developed by researchers at the US Army Research Laboratory (ARL) and Carnegie Mellon University in the US, helps quickly teach robots novel behaviours with minimal human oversight.

"If a robot acts as a teammate, tasks can be accomplished faster and more situational awareness can be obtained," said Maggie Wigness, from ARL.

"Further, robot teammates can be used as an initial investigator for potentially dangerous scenarios, thereby keeping Soldiers further from harm," said Wigness.

To achieve this, Wigness said the robot must be able to use its learned intelligence to perceive, reason and make decisions.

"This research focuses on how robot intelligence can be learned from a few human example demonstrations," Wigness said.

"The learning process is fast and requires minimal human demonstration, making it an ideal learning technique for on-the-fly learning in the field when mission requirements change," she said.

Researchers focused their initial investigation on learning robot traversal behaviours with respect to the robot's visual perception of terrain and objects in the environment.

More specifically, the robot was taught how to navigate from various points in the environment while staying near the edge of a road, and also how to traverse covertly using buildings as cover.

According to the researchers, given different mission tasks, the most appropriate learned traversal behaviour can be activated during robot operation.

This is done by leveraging inverse optimal control, also commonly referred to as inverse reinforcement learning, which is a class of machine learning that seeks to recover a reward function given a known optimal policy.

In this case, a human demonstrates the optimal policy by driving a robot along a trajectory that best represents the behaviour to be learned.

These trajectory exemplars are then related to the visual terrain/object features, such as grass, roads and buildings, to learn a reward function with respect to these environment features.

While similar research exists in the field of robotics, what ARL is doing is especially unique.

"The challenges and operating scenarios that we focus on here at ARL are extremely unique compared to other research being performed," Wigness said.

"We seek to create intelligent robotic systems that reliably operate in warfighter environments, meaning the scene is highly unstructured, possibly noisy, and we need to do this given relatively little a priori knowledge of the current state of the environment," she said.

The research is crucial for the future battlefield, where soldiers will be able to rely on robots with more confidence to assist them in executing missions.

(This story has not been edited by Devdiscourse staff and is auto-generated from a syndicated feed.)

Download The Devdiscourse News App for Latest News.



WEF2020: Trump seems politically correct in pulling out from Paris Agreement

If the survey of the World Economic Forum WEF is believed, Trump seems to enjoy the confidence of his people in flaying climate intuitions and climate activists. His preference for economic development over environmental protection not only...

From home to healthcare, here are Robotic innovations transforming lives

Lovot is equipped with more than 50 sensors such as thermography, microphone array, obstacle detection, and touch sensor to generate motion and emotions in real-time....

Translating words to deeds: Achieving gender parity in access to financial resources

... ...

SDG13: How you can reduce global warming by changing your food habits

The mega narratives of various international organizations give the impression that fighting global warming is only a job of government agencies. However, the European Investment Bank EIB has designed a questionnaire which besides making th...


Latest News

Britain must change how land is used to meet climate goal

Britons should plant many more trees, eat less meat, cut food waste and restore peatlands if the country is to meet its climate target of reaching net zero emissions by 2050, the governments climate advisers said on Thursday.Britain last ye...

UPDATE 1-China fails to repatriate North Korea workers despite UN sanctions -U.S. official

China has failed to send home North Korean workers by a December deadline in violation of United Nations sanctions, a senior U.S. official said on Wednesday, adding that this was why Washington blacklisted two entities involved in Pyongyang...

U.S.'s Pompeo says real reform key to international aid for Lebanon

U.S. Secretary of State Mike Pompeo said on Wednesday only a Lebanese government capable and committed to undertaking real and tangible reforms will restore investor confidence and unlock international assistance.In a statement, Pompeo also...

Taylor Swift, Olivia Colman lead diverse Sundance 2020 lineup

Women directors and stars will be at the forefront of this years Sundance Film Festival starting on Thursday, at a time when a lack of diversity among nominees has been the focus of the Hollywood awards season.Women directed 44 of the 118 f...

Give Feedback