Imagine Having a Robotic Teammate

The concept might seem unsettling but prepare yourself for the situation in which task teams will no longer be composed of humans only. In the foreseeable future, robots may play a significant role as members in hybrid (humans & robots) teams, performing mutual tasks. While it is still too early to determine if machines will completely dominate human tasks, the current innovations indicate a wave of advanced AI technologies that are reshaping the way we collaborate. It’s an exciting yet uncertain time as humanity may be on the verge of a critical transformation.

In this developing/changing environment, some remarkable innovations stem from Elbit Systems’ robotics branch’s tireless efforts. Eli, R&D Programs Manager at the CTO Office of Elbit Systems’ C4I and Cyber division, sheds light on one of the pivotal features on which he and his colleagues have been focusing recently.

“Robots have already become integral members of various army units worldwide over the past couple of decades,” he explains. “Our challenge is to gain relevant social skills needed for a mission robot, to naturally and fluently interact with human teams, using non-verbal and verbal communication, to improve collaboration when performing mutual tasks, in dynamic environments.”

“In simpler terms, his team has been tirelessly working on a ground robotic platform that soldiers can interact with naturally, as if they were talking to their human fellow teammates. Eli stated, “We also need to deliver adaptive autonomy – adjusting the robot’s operational autonomy level to the relevant user(s) and its way to control the task, leveraging advanced situational perception and context-awareness, using explainable, trustworthy AI models.”

Taking Robotics to the Next Level

Until recently, incorporating a robot into a task team meant having a team member with specialized skills to operate a unique device with a joystick or other control methods. However, Elbit’s R&D team are now pursuing a new idea – abandoning the need for a dedicated controlling device and relying solely on natural communication means (speech, gestures). This way, every soldier in the team can interact with the robotic platform. “Our goal was to enable soldiers to talk to the robot naturally, have it understand their needs and responds swiftly and efficiently,” Eli adds.

The advanced robotic technology not only comprehends spoken language but also operates based on social codes and etiquette. “Making it seamlessly blend in as an organic team member is crucial,” he emphasizes. However, one question that naturally arises is – how do you teach a robot to grasp human body-language, hierarchy, and manners?

This ambitious and multidisciplinary R&D program requires a harmonious union of scientific prowess and the fascinating world of social science. To ensure the robot comprehends human language, including non-verbal gestures and behaviors, several social science experts have joined the R&D team.

“Having these experts on board enables us to build the infrastructure that facilitates natural communication between autonomous platforms and human task teams,” Eli elaborates. “This helps the robot gain soldiers’ trust and confidence, and operate in a more human-like manner, optimizing their mission-based relationship.”

The development teams had to tap into another challenge of using Large Language Models (LLM) in an offline environment. These algorithms, featuring extensive human-machine dialogue data, require a constant internet connection which isn’t available during outdoor operations. But fear not, as Elbit Systems’ team has found a solution to this predicament. “We’ve ensured that the data our robot requires to function effectively is readily available even offline. That’s what sets our technologies apart,” he explains.

Non Human-Like Robots are better mates

When we envision service robots for task teams, many of us would naturally picture human-like androids. Surprisingly, research shows that this may not be the best approach. According to Eli, “When soldiers see a humanoid robot on their team, they tend to expect it to have full human abilities, which isn’t the case. So, non-humanoid platforms could be more effective in such tasks, allowing soldiers to better recognize and use their unique strengths. The future of such robotics might lie in embracing diverse forms rather than just mimicking humans”.

In his view, the future of service robots revolves around machines that completely steer away from human-like look. To illustrate this, he draws a comparison between how we treat an iRobot machine versus how we treat a human cleaning aid. “To unleash the full potential of these solutions,” he emphasizes, “human team members must always bear in mind that they are dealing with a robot, even if it can communicate in their language and behave accordingly.”

While certain companies strive to integrate humanoid robots into our daily lives, the scenario shifts drastically when it concerns outdoor tasks. “I firmly believe that we are on the brink of a transformation in this field. In fact, this transformation has already commenced, and there’s no turning back,” asserts Eli. “Our task has always been to ensure that our products added value to our customers and are the best in the market.”

The content of the article does not constitute business or financial information about Elbit Systems Ltd. (the “Company”) and is not intended to be a basis for making investment decisions in the Company’s securities. In order to obtain business or financial information about the Company, please refer to the reports and filings that the Company regularly publishes on the website of the U.S Securities and Exchange Commission (EDGAR) and on the notification system of the Tel Aviv Stock Exchange (Maya). 

The article may contain forward-looking statements such as estimates, forecasts, estimates, plans, etc. that refer to future events that are considered forward-looking information as defined under the securities laws of Israel and the United States. There is no certainty that such information will be realized, in whole or in part, and the actual result may differ from what was presented in the article, among other things due to its dependence on external factors that are not under the control of the Company and that cannot be evaluated in advance. The forward-looking statements are based on the Company’s estimates at the time of publication, and the Company has no obligation to update or correct this data.