Search

Human visual scene understanding is so remarkable that we are able to recognize a revisited place when entering it from the opposite direction it was first visited, even in the presence of extreme variations in appearance. This capability is especially apparent during driving: a human driver can recognize where they are when travelling in the reverse direction along a route for the first time, without having to turn back and look. The difficulty of this problem exceeds any addressed in past appearance- and viewpoint-invariant visual place recognition (VPR) research, in part because large parts of the scene are not commonly observable from opposite directions. Consequently, as shown in this paper, the precision-recall performance of current state-of-the-art viewpoint- and appearance-invariant VPR techniques is orders of magnitude below what would be usable in a closed-loop system. Current engineered solutions predominantly rely on panoramic camera or LIDAR sensing setups; an eminently suitable engineering solution but one that is clearly very different to how humans navigate, which also has implications for how naturally humans could interact and communicate with the navigation system. In this paper we develop a suite of novel semantic- and appearance-based techniques to enable for the first time high performance place recognition in this challenging scenario. We first propose a novel Local Semantic Tensor (LoST) descriptor of images using the convolutional feature maps from a state-of-the-art dense semantic segmentation network. Then, to verify the spatial semantic arrangement of the top matching candidates, we develop a novel approach for mining semantically-salient keypoint correspondences.

This paper presents a real-time, object-independent grasp synthesis method which can be used for closed-loop grasping. Our proposed Generative Grasping Convolutional Neural Network (GG-CNN) predicts the quality and pose of grasps at every pixel. This one-to-one mapping from a depth image overcomes limitations of current deep-learning grasping techniques by avoiding discrete sampling of grasp candidates and long computation times. Additionally, our GG-CNN is orders of magnitude smaller while detecting stable grasps with equivalent performance to current state-of-the-art techniques. The light- weight and single-pass generative nature of our GG-CNN allows for closed-loop control at up to 50Hz, enabling accurate grasping in non-static environments where objects move and in the presence of robot control inaccuracies. In our real-world tests, we achieve an 83% grasp success rate on a set of previously unseen objects with adversarial geometry and 88% on a set of household objects that are moved during the grasp attempt. We also achieve 81% accuracy when grasping in dynamic clutter.

Lance-Adams syndrome or chronic post-hypoxic myoclonus, is a rare complication of post-cardiopulmonary resuscitation, accompanied by action myoclonus and cerebellar ataxia. It manifests as diffuse action-triggered jerking movements resulting in significant morbidity. A case of Lance-Adams syndrome is presented here in a 60-year-old farmer admitted to the intensive care unit with history of cobra bite, in coma and respiratory failure, revived elsewhere. His EEG and CT brain was unremarkable. This patients myoclonus was poorly controlled by a variety of anti-epileptic medications. Over 75 days of rehabilitation there was improvement in ambulation and there were no cognitive deficits.

Lance-Adams syndrome or chronic post-hypoxic myoclonus, is a rare complication of post-cardiopulmonary resuscitation, accompanied by action myoclonus and cerebellar ataxia. It manifests as diffuse action-triggered jerking movements resulting in significant morbidity. A case of Lance-Adams syndrome is presented here in a 60-year-old farmer admitted to the intensive care unit with history of cobra bite, in coma and respiratory failure, revived elsewhere. His EEG and CT brain was unremarkable. This patients myoclonus was poorly controlled by a variety of anti-epileptic medications. Over 75 days of rehabilitation there was improvement in ambulation and there were no cognitive deficits.

This study aimed to compare vocal fold elasticity data from a new method for non-invasive analysis by stimulations of the mucosa with short air pulses. The depth of the mucosal deflections is measured with laser pulses by means of a special algorithm. Ten scarred New Zealand rabbit vocal folds and four normal rabbit folds were measured directly after sacrifice. The elastic data were compared to histological sections from the scarred vocal folds analysed by a pathologist. The results showed significantly lower elasticity (higher stiffness) values for the more scarred vocal folds as compared to samples with minor damage (P=0.03). It is concluded that the air pulse stimulation method is a promising tool for non-invasive quantification of vocal fold scarring.