Search for: All records

Robots can use auditory, visual, or haptic interfaces to convey information to human users. The way these interfaces select signals is typically pre-defined by the designer: for instance, a haptic wristband might vibrate when the robot is moving and squeeze when the robot stops. But different people interpret the same signals in different ways, so that what makes sense to one person might be confusing or unintuitive to another. In this paper we introduce a unified algorithmic formalism for learningco-adaptiveinterfaces fromscratch. Our method does not need to know the human’s task (i.e., what the human is using these signals for). Instead, our insight is that interpretable interfaces should select signals that maximizecorrelationbetween the human’s actions and the information the interface is trying to convey. Applying this insight we develop LIMIT: Learning Interfaces to Maximize Information Transfer. LIMIT optimizes a tractable, real-time proxy of information gain in continuous spaces. The first time a person works with our system the signals may appear random; but over repeated interactions the interface learns a one-to-one mapping between displayed signals and human responses. Our resulting approach is both personalized to the current user and not tied to any specific interface modality. We compare LIMIT to state-of-the-art baselines across controlled simulations, an online survey, and an in-person user study with auditory, visual, and haptic interfaces. Overall, our results suggest that LIMIT learns interfaces that enable users to complete the task more quickly and efficiently, and users subjectively prefer LIMIT to the alternatives. See videos here:https://youtu.be/IvQ3TM1_2fA. 

Regular user interface screens can display dense and detailed information to human users but miss out on providing somatosensory stimuli that take full advantage of human spatial cognition. Therefore, the development of new haptic displays can strengthen human-machine communication by augmenting visual communication with tactile stimulation needed to transform information from digital to spatial/physical environments. Shape-changing interfaces, such as pin arrays and robotic surfaces, are one method for providing this spatial dimension of feedback; however, these displays are often either limited in maximum extension or require bulky mechanical components. In this paper, we present a compact pneumatically actuated soft growing pin for inflatable haptic interfaces. Each pin consists of a rigid, air-tight chamber, an inflatable fabric pin, and a passive spring-actuated reel mechanism. The device behavior was experimentally characterized, showing extension to 18.5 cm with relatively low pressure input (1.75 psi, 12.01 kPa), and the behavior was compared to the mathematical model of soft growing robots. The results showed that the extension of the soft pin can be accurately modeled and controlled using pressure as input. Finally, we demonstrate the feasibility of implementing individually actuated soft growing pins to create an inflatable haptic surface. 

Haptics devices have been developed in a wide range of form factors, actuation methods, and degrees of freedom, often with the goal of communicating information. While work has investigated the maximum rate and quantity of information that can be transferred through haptics, these measures often do not inform how humans will use the devices. In this work, we measure the differences between perception and use as it relates to signal complexity. Using an inflatable soft haptic display with four independently actuated pouches, we provide navigation directions to participants. The haptic device operates in three modalities, in increasing order of signal complexity: Cardinal, Ordinal, and Continuous. We first measure participants’ accuracy in perceiving continuous signals generated by the device, showing average errors below 5 deg. Participants then used the haptic device in each operating mode to guide an object towards a target in a 2-dimensional plane. Our results indicate that human’s use of haptic signals often lags significantly behind the displayed signal and is less accurate than their static perception. Additionally signal complexity was correlated with path efficiency but inversely correlated with movement speed, showing that even simple design changes create complex tradeoffs. 

Physical interaction between humans and robots can help robots learn to perform complex tasks. The robot arm gains information by observing how the human kinesthetically guides it throughout the task. While prior works focus on how the robot learns, it is equally important that this learning is transparent to the human teacher. Visual displays that show the robot’s uncertainty can potentially communicate this information; however, we hypothesize that visual feedback mechanisms miss out on the physical connection between the human and robot. In this work we present a soft haptic display that wraps around and conforms to the surface of a robot arm, adding a haptic signal at an existing point of contact without significantly affecting the interaction. We demonstrate how soft actuation creates a salient haptic signal while still allowing flexibility in device mounting. Using a psychophysics experiment, we show that users can accurately distinguish inflation levels of the wrapped display with an average Weber fraction of 11.4%. When we place the wrapped display around the arm of a robotic manipulator, users are able to interpret and leverage the haptic signal in sample robot learning tasks, improving identification of areas where the robot needs more training and enabling the user to provide better demonstrations. See videos of our device and user studies here: https://youtu.be/tX-2Tqeb9Nw