Separated by a Common Language: How the Nature of Code Differences Shapes Communication Success and Code Convergence

Coordinated action within and beween organizations is easier when individuals share communication codes—mappings between stimuli and labels. Because codes are specific to the groups within which they arise as conventions, collaboration across organizational units that have developed their own distinctive codes is often difficult. However, not all code differences are equal in their implications for communication difficulty and the capacity of individuals starting out with different codes to develop a shared code. Using computational models, we develop a theory about the nature of differences in initial communication codes and how they impact convergence on a common code. Our results show that the difficulty of code convergence lies not as much in learning new codes as in unlearning existing ones. The most severe challenges to communication stem from “code clashes” where codes contain different mappings between the same labels and stimuli. Furthermore, clashes that arise when agents have developed their individual codes in different task environments but draw on a common set of labels are likely to be the hardest to recover from, reflecting the perils of being “separated by a common language.” This paper was accepted by Lamar Pierce, organizations.

Task space adaptation via the learning of gait controllers of magnetic soft millirobots

Untethered small-scale soft robots have promising applications in minimally invasive surgery, targeted drug delivery, and bioengineering applications as they can directly and non-invasively access confined and hard-to-reach spaces in the human body. For such potential biomedical applications, the adaptivity of the robot control is essential to ensure the continuity of the operations, as task environment conditions show dynamic variations that can alter the robot’s motion and task performance. The applicability of the conventional modeling and control methods is further limited for soft robots at the small-scale owing to their kinematics with virtually infinite degrees of freedom, inherent stochastic variability during fabrication, and changing dynamics during real-world interactions. To address the controller adaptation challenge to dynamically changing task environments, we propose using a probabilistic learning approach for a millimeter-scale magnetic walking soft robot using Bayesian optimization (BO) and Gaussian processes (GPs). Our approach provides a data-efficient learning scheme by finding the gait controller parameters while optimizing the stride length of the walking soft millirobot using a small number of physical experiments. To demonstrate the controller adaptation, we test the walking gait of the robot in task environments with different surface adhesion and roughness, and medium viscosity, which aims to represent the possible conditions for future robotic tasks inside the human body. We further utilize the transfer of the learned GP parameters among different task spaces and robots and compare their efficacy on the improvement of data-efficient controller learning.