Human Centered Robotics

-- started MarkCutkosky - 17 Oct 2008

Vision Focus Management

The Stanford Consortium for Human-Centered Robotics is a new program focused on robotics that interact directly with people.

human-safe robots

human-robot interactivity

The goal of human-safe robots is that they should be inherently incapable of causing harm to people. The primary challenge is to create robots that are inherently safe while also being strong, fast and precise enough to do useful work in a human environment.

Safety is achieved through a combination of active and passive methods, including materials, structures, sensors, actuators, controllers and algorithms for perception and adaptation.

Areas of particular interest include:

• Application of Rapid Prototyping Techniques such as Shape Deposition Manufacturing for strong yet lightweight robotic manipulators.
• Development of proximity sensors and algorithms to enable safe control of robotic platforms in dynamic environments.
• High performance inherently safe actuation scheme
• Cooperation schemes for human-robot interactions for increased productivity

From discusssion with Khatib, the program will not be just about human safe robots. Rather, it is the application of technology for human interfaces. He feels the scope should expand include assistance, facilitation and interaction research, not just a platform. It will incorporate understanding human motion through modelling, perception and sensing, etc. He mentioned looking at KAUST for inspiration -- SamsonPhan - 27 Oct 2008

Just a few paragraphs on what the white paper might be like (borrowing heavily from the GM white paper)

In recent years, there has been increased interest in the emerging field of human-centered robotics, involving close physical interaction between robots and humans. The applications include important areas such as medical robots, manufacturing, and entertainment. In-home robotics will maintain the independence of a burgeoning aging population. Greater human-robot interaction will allow manufacturers to capitalize on the synergistic relationship, combining the judgment of human workers with the speed and precision of robotic platforms for greater productivity and efficiency. A major challenge in the development of human-centered robotics is safety: How can robots be sufficiently strong, precise and dexterous to do useful work while also being inherently safe for physical interaction?

Critical technologies needed for greater robotic presence in human environments include a “smart” skin. Bioinspired by our own epidermis, this outer layer will enable environmental sensing, allowing for active collision avoidance. Capacitive based sensors under development will improve on Mother Nature’s design, enabling sensing long before physical contact is made. Development of large skin sensor arrays poses a new concern for robot control, a dearth of environmental data. Innovative control schemes must be developed to enable incorporation of this data. Such “awareness” will enable operation of robotic platforms at maximum productivity while ensuring people safety.

Development of human safe robotic platforms will utilize strong yet lightweight structures using rapid prototyping techniques such as Shape Deposition Manufacturing (SDM). SDM allows multiple materials, as well as sensors, actuators and other discrete parts, to be integrated in a single heterogeneous structure. The technology has been demonstrated for various bio-inspired robots in Cutkosky’s lab. The ability of SDM to provide local variations in materials properties also permits structures with high specific strength and stiffness in selected areas while providing high impact energy absorption in other areas.

Our group has investigated new actuation techniques to overcome the safety and performance limitations of existing technologies. We have developed the distributed macro–mini (DM2) actuation approach to address the problem of a large reflected inertia by partitioning torque generation into low- and high-frequency domains, which are controlled by distributed pairs of actuators. Two prototypes were developed to extend the DM2 approach to a combination of pneumatic and electromagnetic actuation. Pneumatic McKibben? actuators provide high power and force density and inherently low mechanical impedance. However, the underlying nonlinear compressible gas dynamics involved make precise control difficult. By combining them with small electromagnetic actuators we were able to achieve a 10-fold reduction in effective inertia while maintaining high-frequency torque capability. The combination of two different actuation technologies comes at the expense of complexity in comparison to traditional robot design. To make this complexity manageable, we use miniaturized integrated pressure controllers and multi-material structures. A controller using micro-valves and pressure sensors adapted from ink-jet printing technology is much lighter and more compact than a traditional pressure controller. By linking the pressure controllers with a single pressure line, we are further able to reduce the weight and part count. Previous experience in Mckibben actuation technology has enabled the development of actuators with significant performance improvement over existing commercial products enabling higher bandwidth and greater force while still maintaining the inherent compliance characteristics.

-- SamsonPhan - 20 Oct 2008

Investigation into Human-Robot impacts will also be a component of the proposed research. This research will determine the limits at which robots can work without imposing a danger to their human counterparts. Preliminary research have identified limits in tool sharpness, manipulator velocity, and the effectiveness of decreased inertia in reducing head injuries.

The ideal humanoid robot platform will require minimal user learning; interaction should be intuitive. -- SamsonPhan - 14 Nov 2008