Search

The ability to sense compliant interactions through internal state measurements improves adaptability and robustness of robotic grasping and manipulation, without interfering with any carefully designed passive dynamics. This work presents a collocated sensing and actuation system using a compliant tendon driven hand and its accompanying model. Using a simple vision-based measurement device the approach is able to estimate its internal state and applied external forces. The camera-based sensor uses off-the-shelf components and has the ability to measure many more than 15 tendons simultaneously, giving a low-cost, scale-able, high-bandwidth sensing solution. The collocated configuration provides a framework for developing stable feedback controllers. Our results show that the system can estimate change in posture with $\lt 10$% error with the potential to estimate contact forces using the same scheme.

Soft strain sensors are becoming increasingly popular for obtaining tactile information in soft robotic applications. Diverse technological solutions are being investigated to design these sensors. Simultaneously, new methods for modeling these sensor are being proposed due to their highly nonlinear, time varying properties. Among them, machine learning based approaches, particularly using dynamic recurrent neural networks look the most promising. However, these complex networks have large number of free parameters to be tuned, making it difficult to apply them for real-world applications. This paper introduces the concept of transfer learning for modelling soft strain sensors, which allows us to utilize information learned in one task to be applied to another task. We demonstrate this technique on a passive anthropomorphic finger with embedded strain sensors used for two regression tasks. We show how the transfer learning approach can drastically reduce the number of free parameters to be tuned for learning new skills. This work is an important step towards scaling of sensor networks (algorithm-wise) and for using soft sensor data for high-level control tasks.

With advances in the field of robotic manipulation, sensing and machine learning, robotic chefs are expected to become prevalent in our kitchens and restaurants. Robotic chefs are envisioned to replicate human skills in order to reduce the burden of the cooking process. However, the potential of robots as a means to enhance the dining experience is unrecognised. This article introduces the concept of food quality optimization and its challenges with an automated omelette cooking robotic system. The design and control of the robotic system that uses general kitchen tools is presented first. Next, we investigate new optimization strategies for improving subjective food quality rating, a problem challenging because of the qualitative nature of the objective and strongly constrained number of function evaluations possible. Our results show that through appropriate design of the optimization routine using Batch Bayesian Optimization, improvements in the subjective evaluation of food quality can be achieved reliably, with very few trials and with the ability for bulk optimization. This study paves the way towards a broader vision of personalized food for taste-and-nutrition and transferable recipes. © 2016 IEEE.

Soft robotic systems are primarily characterized by their low stiffness properties. However, for these high dimension nonlinear systems, it becomes increasingly difficult to define and estimate stiffness properties. This paper presents a methodology to estimate the dominant compliance of a soft robotic manipulator using only motion information. We show how this information can be used for input shaping to suppress unwanted vibrations during point to point motion. Furthermore the methodology can be used to assess manipulator design and stiffening mechanisms.