At many organizations, the implementation of security technology goes hand-in-hand with the employment of security officers. Guards are trained to become proficient in the use of myriad systems - video surveillance, access control, visitor management, intrusion detection, etc. – so that they can provide the highest level of premisis security possible. After all, who else is going to be on site to determine if a tripped sensor is an intruder trying to enter the facility or just a false alarm? Advancements in surveillance technology have enabled an unprecedented level of remote connectivity and the ability to conduct “virtual guard tours,” but they are still not an adequate replacement for a security officer in many circumstances.
What if, however, there was a possibility that guards could be replaced by artificial intelligence? It may sound like science fiction, but British researchers are heading up a project funded by the European Union that endeavors to give robots the ability to learn and adapt to their environment. The £7.2 million STRANDS project, which is being led by the School of Computer Science at the University of Birmingham in the UK, aims to overcome the limitations of current robotic technologies by enabling them to work for longer periods of time (at least 120 days), thereby giving them an opportunity to learn about the world around them.
Dr. Nick Hawes, a lecturer in intelligent robotics at the University of Birmingham, will coordinate the research project, according to a statement issued by the university.
“Recent advances in robotics and artificial intelligence have enabled mobile robots to operate intelligently in predictable environments for limited periods of time. Our challenge is to develop robots which can go way beyond this, running reliably in dynamic real-world security and care environments for as long as they’re required,” Hawes said in the statement. “This will make these machines truly useful assistants in our workplaces. However to do this, we must make great leaps forward in understanding how robots can understand their worlds using the information their sensors provide. For this problem, long run times are essential as they allow the robots to learn what normally happens around them every day.”
Robots developed by the research team will be tested at two sites; an elderly care facility in Austria and an office environment patrolled by officers from guard services firm G4S in the UK. G4S Technology is a partner in the STRANDS consortium which involves three universities in the UK, plus universities in Germany, Austria and Sweden. G4S is providing expertise to guide the researchers into producing the right capabilities for the intelligent patrolling robot of the future.
“The idea is to create service robots that will work with people and learn from long-term experiences,” Professor Tom Duckett, director of the Lincoln Centre for Autonomous Systems Research, said in the statement. Duckett will be responsible for leading research on creating 4D maps of the environments, as well as methods for detecting changes and unusual situations.
“What’s unusual about any environment depends on the context,” he added. “In a security scenario, a robot will be required to perform regular patrols and continually inspect its surroundings for variations from its normal experiences. Certain changes, such as finding a person in a restricted area, may indicate a security violation or a burglary. In a care home, a robot will be required to act as an assistant for elderly patients, fetching and carrying things while also being alert to incidents such as people falling over. It’s not just about developing a care home or security robot. We are trying to enable robots to learn from their long-term experience and their perception of how the environment unfolds in time. The technology will have many possible applications.”
According to David Ella, vice president, technology marketing for G4S Technology, the introduction of robotic technology in the guard services industry will not eliminate the need for human security officers.
“Guard services are just part of the rapidly changing world we are all experiencing and technology advances are starting to come really quickly. It’s now the norm for the larger security services organizations like G4S to offer mobile devices – usually Android cell phones – with each security officer, loaded with applications that add value to the security officer on the ground,” Ella said. “Over the last 10 years, we have seen the growth of security cameras in customer facilities and security officers are already using those cameras for patrol purposes. There comes to be a natural balance of the optimum number of security officers and cameras. One of the great possibilities of a robot is that it can actually be a mobile camera, so a security officer could send a robot out to the source of an alarm – such as a door held open alarm from an access control system – to check out what’s going on and see if a human response is required.
“There will always be human guards, but we have to remember that guards carry out a wide range of functions. They are not just the most visible armed officers standing outside banking centers. Sometimes, security officers takeover straightforward business processes within organizations such as delivering post and even maintenance tasks. Who is to say that in a few years time some of these operations couldn’t be carried out by a robot?”
Lew Pincus, senior director, marketing and communications for G4S Secure Solutions USA, says that modern day security officers are becoming more integrated with business processes within organizations.
“For instance at G4S, our security officers are equipped with powerful software called Secure Trax on their mobile device that can perform tasks like safety inspections, real-time incident reporting, record pictures, receive alerts (BOLO’s), and post order updates,” Pincus explained. “Other technology advancements like RISK360 allow customers to see risk through data that is collected from incidents, and other data that is collected, interpreted and managed giving the organization actionable data to mitigate risk using continuous improvement processes.
Although the regular use of robots in security environments may not take place until well into the future, Ella says the potential they offer cannot be ignored.
“We can’t stick our heads in the sand and ignore technologies as they come along. Robots that can genuinely add value and assist human security officers are a long way off – maybe 10 years – but we know they are coming,” Ella said. “That’s why G4S has got involved in the STRANDS project. We are using this opportunity to guide academic researchers into the real needs of the security industry and our customers, so they are not targeting a Hollywood-style vision of the future.
Additionally, Ella says many of the tasks performed by human guards simply cannot be replicated by any currently available robotic technology.
“Our expectations of the capabilities of robots are colored by our experience of robots in movies, but the reality today is that a robot has the memory and understanding of its world similar to that of a goldfish. Security officers patrolling an area need to identify situations that are not normal; windows open, water leaks, disturbed property and intruders outside permitted hours are good examples. However, to know what is abnormal, the robot needs to have a really good understanding of what is normal and that artificial intelligence of learning the environment and how it changes over time is what the STRANDS project is building up,” Ella said. “Human security officers carry out a very wide range of tasks and a large number of them require interaction with members of the public and other employees – face-to-face and by telephone. Robots aren’t so good at that at the moment. Humans are very good at adapting to changing circumstances whereas robots like routine, so we are a long way off replacing the security officer as we know them today. That’s not to say that a robot couldn’t work alongside a security officer to provide another set of eyes and ears and we do see that technology coming maybe in the next 10 or 15 years. Robots have a lot of limitations today and a lot of work is needed before they can be used in normal buildings. It’s actually quite straightforward for a robot to use an elevator by linking the robot control system to an access control system, but robots are not so good with stairs and door handles just for a start.”