Mario A. Bollini

Interpreting and Executing Recipes with a Cooking Robot

The creation of a robot chef represents a grand challenge for the field of robotics. Cooking is one of the most important activities that takes place in the home, and a robotic chef capable of following arbitrary recipes would have many applications in both household and industrial environments. The kitchen environment is a semi-structured proving ground for algorithms in robotics. It provides many computational challenges, such as accurately perceiving ingredients in cluttered environments, manipulating objects, and engaging in complex activities such as mixing and chopping.

Indoor robot gardening: design and implementation

This paper describes the architecture and implementation of a distributed autonomous gardening system with applications in urban/indoor precision agriculture. The garden is a mesh network of robots and plants. The gardening robots are mobile manipulators with an eye-in-hand camera. They are capable of locating plants in the garden, watering them, and locating and grasping fruit. The plants are potted cherry tomatoes enhanced with sensors and computation to monitor their well-being (e.g. soil humidity, state of fruits) and with networking to communicate servicing requests to the robots. By embedding sensing, computation, and communication into the pots, task allocation in the system is de-centrally coordinated, which makes the system scalable and robust against the failure of a centralized agent. We describe the architecture of this system and present experimental results for navigation, object recognition, and manipulation as well as challenges that lie ahead toward autonomous precision agriculture with multi-robot teams.

The Design, Fabrication, and Performance of the East African Trial Leveraged Freedom Chair

Massachusetts Institute of Technology. Office of the Dean for Graduate Education (Hugh Hampton Young Memorial Fellowship)

The Design and Testing of a Low-Cost, Globally-Manufacturable, Multi-Speed Mobility Aid Designed for Use on Varied Terrain in Developing and Developed Countries

Mobility aids that are currently available in developing countries do not fully meet users’ needs. People require a device that is maneuverable within the home and that can travel long distances on rough roads. To address this problem, we have designed the Leveraged Freedom Chair (LFC), a wheelchair-based mobility aid capable of navigating virtually any terrain by optimally utilizing upper body power for propulsion through a variable-speed lever drivetrain. The lever system achieves a 4:1 change in mechanical advantage, equating to leverage that ranges from 0.42X to 1.65X a standard wheelchair hand rim. In comparative trials, the LFC demonstrated capabilities that far exceed those of any mobility aid currently available in the developing world; it was able to cruise on smooth surfaces at 2m/s (5mph), climb muddy, grassy hills with a 1:3 slope, and navigate terrain with a coefficient of rolling resistance as high as 0.48. This operational flexibility should make the LFC usable on any terrain, from rural walking paths to tight indoor confines, and greatly increase the mobility of people with disabilities in developing countries. The LFC may also be attractive to wheelchair users in developed countries, as its performance breadth exceeds that of currently available products.Copyright

Stakeholder-Driven Design Evolution of the Leveraged Freedom Chair Developing World Wheelchair

The Leveraged Freedom Chair (LFC) is a low-cost, all-terrain, variable mechanical advantage, lever-propelled wheelchair designed for use in developing countries. The user effectively changes gear by shifting his hands along the levers; grasping near the ends increases torque delivered to the drivetrain, while grasping near the pivots enables a larger angular displacement with every stroke, which increases angular velocity in the drivetrain and makes the chair go faster. This paper chronicles the design evolution of the LFC through three user trials in East Africa, Guatemala, and India. Feedback from test subjects was used to refine the chair between trials, resulting in a device 9.1 kg (20 lbs) lighter, 8.9 cm (3.5 in) narrower, and with a center of gravity 12.7 cm (5 in) lower than the first iter