Tunable Neural Encoding of a Symbolic Robotic Manipulation Algorithm

We present a neurocomputational controller for robotic manipulation based on the recently developed “neural virtual machine” (NVM). The NVM is a purely neural recurrent architecture that emulates a Turing-complete, purely symbolic virtual machine. We program the NVM with a symbolic algorithm that solves blocks-world restacking problems, and execute it in a robotic simulation environment. Our results show that the NVM-based controller can faithfully replicate the execution traces and performance levels of a traditional non-neural program executing the same restacking procedure. Moreover, after programming the NVM, the neurocomputational encodings of symbolic block stacking knowledge can be fine-tuned to further improve performance, by applying reinforcement learning to the underlying neural architecture.

Impact of Early Exposure to Robotic Surgery Among Pre-clinical Medical Students on Career Choice and Simulation Skills

We aimed to assess whether early exposure of medical students to robotic surgery training influences their interest in a surgical career and improves scores on objective simulation tasks. Medical students were invited to participate in robotic online training modules, robotic simulation exercises followed by a hands-on robotic dry-lab session. Pre- and post-simulator scores were recorded. A 29-question anonymous survey was recorded before and after the lab. Seventy percent reported that the training had a positive impact on influencing their decision to pursue a general surgery career. Students showed significantly improved skill and performance on simulation activities post-training. After the training, students felt knowledgeable about robotics, more comfortable operating robotically, and thought that robotic surgery would hold a significant place in the future of surgery. Exposing students to robotic training positively impacts their perception of surgery as a career choice and results in improvement in objective scores on simulation tasks.

Self-Organised Collision-Free Flocking Mechanism in Heterogeneous Robot Swarms

Flocking is a social animals’ common behaviour observed in nature. It has a great potential for real-world applications such as exploration in agri-robotics using low-cost robotic solutions. In this paper, an extended model of a self-organised flocking mechanism using heterogeneous swarm system is proposed. The proposed model for swarm robotic systems is a combination of a collective motion mechanism with obstacle avoidance functions, which ensures a collision-free flocking trajectory for the followers. An optimal control model for the leader is also developed to steer the swarm to a desired goal location. Compared to the conventional methods, by using the proposed model, the swarm network has less requirement for power and storage. The feasibility of the proposed self-organised flocking algorithm is validated by realistic robotic simulation software.

A Transfer Entropy Based Approach for Fault Isolation in Industrial Robots

In this paper, we cast the problem of fault isolation in industrial robots as that of causal analysis within coupled dynamical processes and evaluate the efficacy of the information theoretic approach of transfer entropy. To create a realistic and exhaustive dataset, we simulate wear induced failure by increasing friction coefficient on select axes within an in-house robotic simulation tool that incorporates an elastic gearbox model. The source axis of failure is identified as one which has the highest net transfer entropy across all pairs of axes. In an exhaustive simulation study, we vary the friction successively in each axis across three common industrial tasks: pick and place, spot welding, and arc welding. Our results show that transfer entropy based approach is able to detect the axis of failure more than 80 percent of the time when the friction coefficient is 5% above the nominal value and always when friction coefficient is 10% above the nominal value. The transfer entropy approach is more than twice as accurate as cross-correlation, a classical time-series analysis used to identify directional dependence among processes.

Effects of MOPP Gear on SAM Medical Junctional Tourniquet Application: A Prospective, Randomized Control Trial

Introduction Hemorrhage is the leading cause of preventable death on the battlefield, and hemostasis is particularly challenging to achieve at junctional sites such as the axillary or inguinal regions. Mission-oriented protective posture (MOPP) gear, as worn most recently in Syria to guard against chemical weapons, can make the performance of technical skills more challenging still. The objective of this study was to evaluate how wearing MOPP gear affects the application time of the SAM Medical Junctional Tourniquet (SJT) by U.S. Army combat medics. Materials and Methods We conducted a prospective, randomized control trial evaluating time for SJT application between participants wearing MOPP versus those not wearing MOPP. Secondary outcomes included SJT application success rate and participant appraisal of SJT application difficulty assessed with five-point Likert items, between groups. Participants placed SJTs on robotic simulation mannequins with a penetrating inguinal injury. Results In April 2019, we enrolled 49 combat medics. Most participants were male (77.5%), had a median age of 25 (interquartile range 23–28), and in the grade of E4 or less (63.3%). Mean SJT application times in seconds were higher among those wearing MOPP versus those who were not (223.1 versus 167.2; 95% confidence interval for difference in means 5.293, 106.374; P = 0.03). Participants wearing MOPP had a less successful application rate overall, but this difference was not statistically significant (64.3% versus 81.0%, P = 0.34). Compared to participants not wearing MOPP, those wearing MOPP agreed that SJT application was difficult (4 versus 3, P = 0.03), what they were wearing affected SJT application (4 versus 2, P = 0.01), and it was difficult to use their hands during SJT application (4 versus 1, P < 0.001). Conclusions Wearing military MOPP gear significantly prolongs the amount of time required for combat medics to apply an SJT on a simulated casualty with a penetrating inguinal injury. This study highlights the importance of incorporating MOPP gear into medical training scenarios to improve skills competency while wearing these protective garments.