Related papers: InsertionNet 2.0: Minimal Contact Multi-Step Inser…

New technologies drastically change recruitment techniques. Some research projects aim at designing interactive systems that help candidates practice job interviews. Other studies aim at the automatic detection of social signals (e.g.…

Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that…

Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years. However, efficient and accurate intrusion detection remains a challenging issue due to: (a) limited sample number: only small…

An effective paradigm for simulating the dynamics of robots that locomote and manipulate is multi-rigid body simulation with rigid contact. This paradigm provides reasonable tradeoffs between accuracy, running time, and simplicity of…

The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…

Zero-shot learning transfers knowledge from seen classes to novel unseen classes to reduce human labor of labelling data for building new classifiers. Much effort on zero-shot learning however has focused on the standard multi-class…

Teaching robots novel skills with demonstrations via human-in-the-loop data collection techniques like kinesthetic teaching or teleoperation puts a heavy burden on human supervisors. In contrast to this paradigm, it is often significantly…

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning…

Amodal recognition is the ability of the system to detect occluded objects. Most SOTA Visual Recognition systems lack the ability to perform amodal recognition. Few studies have achieved amodal recognition through passive prediction or…

3D posture estimation is important in analyzing and improving ergonomics in physical human-robot interaction and reducing the risk of musculoskeletal disorders. Vision-based posture estimation approaches are prone to sensor and model…

In this paper, we examined the zero-shot activity recognition task with the usage of videos. We introduce an auto-encoder based model to construct a multimodal joint embedding space between the visual and textual manifolds. On the visual…

Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Learning agents struggle to learn in such multisensory settings, especially amidst sensory noise and…

We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion…

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within…

As robots become increasingly prominent in diverse industrial settings, the desire for an accessible and reliable system has correspondingly increased. Yet, the task of meaningfully assessing the feasibility of introducing a new robotic…

Many hand-held or mixed reality devices are used with a single sensor for 3D reconstruction, although they often comprise multiple sensors. Multi-sensor depth fusion is able to substantially improve the robustness and accuracy of 3D…

Deep learning models have become increasingly useful in many different industries. On the domain of image classification, convolutional neural networks proved the ability to learn robust features for the closed set problem, as shown in many…

Manipulation of deformable objects is a challenging task for a robot. It will be problematic to use a single sensory input to track the behaviour of such objects: vision can be subjected to occlusions, whereas tactile inputs cannot capture…

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form…

Imitation learning is promising for robotic manipulation, but \emph{precise insertion} in the real world remains difficult due to contact-rich dynamics, tight clearances, and limited demonstrations. Many existing visuomotor policies depend…