Prognoses differ but robots and vision are marching beyond the factory floor.
Throughout the world, manufacturing industries use conventional, often vision-guided, robotic systems for tasks such as pick-and-place, welding, or inspection. The Robotic Industries Association (Ann Arbor, MI) reports that North American companies purchased more than 14,000 of these robots in 2004, up 20% from the previous year. Automotive manufacturers accounted for about two-thirds of the total. Increased orders from industries such as food, pharmaceuticals, electronics, aerospace, and life sciences.
With more than 350,000 installed robots, Japan is by far the world leader in deploying conventional robotic systems-more than the U.S., Europe, and the rest of Asia combined, according to the International Federation of Robotics (Paris, France). Yet another trend is taking place in the “nonconventional” robot world that’s equally interesting.
See me, hear me, touch me
Anyone who has seen the videos of ASIMO, the humanoid robot developed by Honda Motor might wonder when these kinds of robots will be available to the consumer and how they will be used. The ASIMO is 120 cm tall, looks something like a miniature astronaut, and can move toward its destination without stopping by comparing any deviation between the input map information and the information obtained about the surrounding area from its floor surface sensor. It can change its path when its floor surface sensor and two vision sensors in its head detect obstacles.
ASIMO can walk at a speed of 1.6 km/h and run at 3 km/h. It can follow the movements of people with its vision sensors, recognize faces it has met, and greet them by name. A smaller rival from Sony, QRIO, can perform similar functions and has been seen in a group giving a handbell-ringing recital. Where indeed are these robots leading us?
At the RoboBusiness conference, held in Cambridge, MA, Paolo Pirjanian, chief scientist and general manager of Evolution Robotics (Pasadena, CA) spoke about the future of the robotics industry. He said that Japan will probably retain its advantage in robotics technology. But he remains skeptical about future applications. “I would not want an ASIMO in my house,” he said. “There is simply no obvious killer application in the home for such a technology.”
What may be in demand, he thinks, are simpler, less-sophisticated products like the automated vacuum cleaner Roomba from iRobot (Burlington, MA). Even then, Pirjanian points out, the cost-constraints of developing these products are enormous. With a $200 retail value, $50 hardware costs, and $10 to $20 for marketing, manufacturing, packaging and shipping, the manufacturer can only hope for a 2% to 4% return.
“Because of this, even sales of over one million units can be regarded as a failure by traditional consumer electronics companies,” Pirjanian said. Thus, robots of the future will not initially resemble ASIMO, or R2D2 of Star Wars movie fame. “Robots of the future will be marketed in subtle ways,” he says, “as embedded products in automobiles, toys, personal assistants, and other applications.”
Already, the automotive industry is embracing machine-intelligence in products such as lane-departure-warning (LDW) systems, which use a vision-based camera and software to monitor the lane markings. “In this way,” said Pirjanian, “embedded robotic systems will be introduced in incremental steps to the consumer. And, indeed, in the future, the automobile may become the ultimate robot.”
Similarly, robotics technology is being embedded into toys such as the AIBO from Sony. “Sony has already deployed a custom version of our company’s ER Vision software in the toy and we’ll work closely with Sony to develop future products,” said Pirjanian.
While some may wonder what these systems have to do with robotics, Pirjanian’s point was that robotics technology will not suddenly appear en masse in sophisticated products such as ASIMO, but rather evolve from less-sophisticated consumer-based applications. Japan’s Ministry of Economy and Industry predicts that humanoid robots will be performing general work in public facilities in Japan by 2018. Pirjanian was skeptical. “Unfortunately, there is no Moore’s law for robotics,’’ he said. “Future developments depend on a number of disparate technologies and such humanoid systems may not appear until 2040.”
CONARD HOLTON is editor in chief of Vision Systems Design; e-mail: [email protected].