Richard Bormann

Introduction: Arthroscopic surgery is the gold standard for cruciate ligament reconstruction in multi-ligament knee injuries. However, hospitals in limited-resource settings often lack arthroscopic-trained surgeons or equipment. Open approaches for treating knee dislocations can overcome many of these limitations.Methodology: This study aims to describe techniques for open approaches in a supine patient to address the cruciate ligaments in multi-ligament knee injuries and to review associated complications and clinical outcomes in a retrospective case series.Results: Ten patients with multi-ligament knee injuries who had undergone open cruciate ligament reconstruction between July 2016 and November 2018 were retrospectively identified. Open approaches were performed owing to the extravasation of arthroscopy fluid into the posterior compartment (3) or a large traumatic arthrotomy (7). Complications and patient-reported outcomes were analysed. Eight of the 10 patients were followed up at 10 months postoperatively (range, 5–23 months). None had iatrogenic neurovascular damage. Median outcomes scores were: visual analogue scale, 45 (range, 0–100); Knee Injury and Osteoarthritis Outcome Score-Physical Function Short Form, 81.4 (range, 75–100); Lysholm, 85 (range, 67–92).Discussion: Open approaches were safe and useful in treating cruciate ligaments and should be considered in arthroscopy fluid extraversion and large traumatic arthrotomies.

Purpose of Review: This review provides a comprehensive overview of machine learning approaches for vision-based robotic grasping and manipulation. Current trends and developments as well as various criteria for categorization of approaches are provided.Recent Findings: Model-free approaches are attractive due to their generalization capabilities to novel objects, but are mostly limited to top-down grasps and do not allow a precise object placement which can limit their applicability. In contrast, model-based methods allow a precise placement and aim for an automatic configuration without any human intervention to enable a fast and easy deployment.Summary: Both approaches to robotic grasping and manipulation with and without object-specific knowledge are discussed. Due to the large amount of data required to train AI-based approaches, simulations are an attractive choice for robot learning. This article also gives an overview of techniques and achievements in transfers from simulations to the real world.

This is "RosCon2013 Track1 Day2 09 - Richard Bormann - Hi Richard - Personalize your Robot" by Open Robotics on Vimeo, the home for high quality videos…