Cable failure tolerant control and planning in a planar reconfigurable cable driven parallel robot.

The addition of geometric reconfigurability in a cable driven parallel robot (CDPR) introduces kinematic redundancies which can be exploited for manipulating structural and mechanical properties of the robot through redundancy resolution. In the event of a cable failure, a reconfigurable CDPR (rCDPR) can also realign its geometric arrangement to overcome the effects of cable failure and recover the original expected trajectory and complete the trajectory tracking task. In this paper we discuss a fault tolerant control (FTC) framework that relies on an Interactive Multiple Model (IMM) adaptive estimation filter for simultaneous fault detection and diagnosis (FDD) and task recovery. The redundancy resolution scheme for the kinematically redundant CDPR takes into account singularity avoidance, manipulability and wrench quality maximization during trajectory tracking. We further introduce a trajectory tracking methodology that enables the automatic task recovery algorithm to consistently return to the point of failure. This is particularly useful for applications where the planned trajectory is of greater importance than the goal positions, such as painting, welding or 3D printing applications. The proposed control framework is validated in simulation on a planar rCDPR with elastic cables and parameter uncertainties to introduce modeled and unmodeled dynamics in the system as it tracks a complete trajectory despite the occurrence of multiple cable failures. As cables fail one by one, the robot topology changes from an over-constrained to a fully constrained and then an under-constrained CDPR. The framework is applied with a constant-velocity kinematic feedforward controller which has the advantage of generating steady-state inputs despite dynamic oscillations during cable failures, as well as a Linear Quadratic Regulator (LQR) feedback controller to locally dampen these oscillations.

Dual-Level Knowledge Distillation via Knowledge Alignment and Correlation.

Knowledge distillation (KD) has become a widely used technique for model compression and knowledge transfer. We find that the standard KD method performs the knowledge alignment on an individual sample indirectly via class prototypes and neglects the structural knowledge between different samples, namely, knowledge correlation. Although recent contrastive learning-based distillation methods can be decomposed into knowledge alignment and correlation, their correlation objectives undesirably push apart representations of samples from the same class, leading to inferior distillation results. To improve the distillation performance, in this work, we propose a novel knowledge correlation objective and introduce the dual-level knowledge distillation (DLKD), which explicitly combines knowledge alignment and correlation together instead of using one single contrastive objective. We show that both knowledge alignment and correlation are necessary to improve the distillation performance. In particular, knowledge correlation can serve as an effective regularization to learn generalized representations. The proposed DLKD is task-agnostic and model-agnostic, and enables effective knowledge transfer from supervised or self-supervised pretrained teachers to students. Experiments show that DLKD outperforms other state-of-the-art methods on a large number of experimental settings including: 1) pretraining strategies; 2) network architectures; 3) datasets; and 4) tasks.

Influence of Morbid Obesity on Surgical Outcomes in Robotic-Assisted Gynecologic Surgery.

Objective: The aim of this research was to estimate the impact of body mass index (BMI) on surgical outcomes in patients undergoing robotic-assisted gynecologic surgery. Materials and Methods: This study was a retrospective review of prospectively collected cohort data for a consecutive series of patients undergoing gynecologic robotic surgery in a single institution. BMI, expressed as kg/m2, was abstracted from the medical charts of all patients undergoing robotic hysterectomy. Data on estimated blood loss (EBL), hemoglobin (Hb) drop, procedure time, length of hospital stay, uterine weight, pain-medication use, and complications were also extracted. Results: Two hundred and eighty-one patients underwent robotic operations. Types of procedures were total hysterectomy with or without adnexal excision, and total hysterectomies with lymphadenectomies. Eighty-four patients who were classified as morbidly obese (BMI>35) were compared with 197 patients who had a BMI of<35 (nonmorbidly obese). For patients with BMI<35, and BMI>35, the mean BMI was 27.1 and 42.5 kg/m2 (p<0.05), mean age was 49 and 50 (p=0.45), mean total operative time was 222 and 266 minutes (p<0.05), console time 115 and 142 minutes (p<0.05), closing time (from undocking until port-site fascia closure) was 30 and 41 minutes (p<0.05), EBL was 67 and 79 mL (p=0.27), Hb drop was 1.6 and 1.4 (p=0.28), uterine weight was 196.2 and 227 g (p=0.52), pain-medication use 93.7 and 111 mg of morphine (p=0.46), and mean length of stay was 1.42 and 1.43 days (0.9), all respectively. No statistically significant difference was noted between the 2 groups for EBL, Hb drop, LOS, uterine weight, pain-medication use, or complications. The only statistically significant difference was seen in operating times and included docking, console, closing, and procedure times. There were no perioperative mortalities. Morbidity occurred in 24 patients (8%). In the morbidly obese group, there were 6 complications (7%) and, in the nonmorbidly obese group, there were 18 complications (9%). Conclusions: Morbid obesity does not appear to be associated with an increased risk of morbidity in patients undergoing robotically assisted gynecologic surgery. Morbid obesity is associated with increased procedure time, but otherwise appears to have no difference in outcomes. Robotic surgery offered an ideal approach, allowing minimally invasive surgery in these technically challenging patients, with no significant increase in morbidity. J GYNECOL SURG 30:81).

Evaluation of robotic minimally invasive surgical skills using motion studies.

Robotic Minimally Invasive Surgery, and the engendered computer-integration, offers unique opportunities for quantitative computer-based surgical-performance evaluation. In this work, we examine extension of traditional manipulative skill assessment, having deep roots in performance evaluation in manufacturing industries, for applicability to robotic surgical skill evaluation. This method relies on: defining task-level segmentation of modular sub-tasks/micro-motions called 'Therbligs' that can be combined to perform a given task; and analyzing intra- and inter-user performance variance by studying surgeons' performance over each 'Therbligs'. Any of the performance metrics of macro-motions-from motion-economy, tool motion measurements to handed-symmetry-can now be extended over the micro-motion temporal segments. Evaluation studies were based on video recordings of surgical tasks in two settings: first, we examined performance of two representative manipulation exercises (peg board and pick-and-place) on a da Vinci surgical SKILLS simulator. This affords a relatively-controlled and standardized test-scenarios for surgeons with varied experience-levels. Second, task-sequences from real surgical videos were analyzed with a list of predefined 'Therbligs' in order to investigate its overall usefulness.

A low-cost framework for individualized interactive telerehabilitation.

In this paper we examine the issues pertaining to development of a low-cost telerehabilitation framework for upper-limb dysfunction, that is suitable for deployment in patients' homes. We use the example of a Virtual Driving Environment (VDE) to present the overall architecture and discuss issues of: (i) quantitative data-acquisition using commercial-off-the-shelf gaming devices; (ii) model-based parametric data transmission/playback; and (iii) parametric biomechanical identification and data reduction; to support individualization within the telerehabilitation regimen.