Related papers: Lifelong 3D Object Recognition and Grasp Synthesis…
Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data…
Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continual learning, is also critical for deep neural networks (DNNs)…
We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network. Our system generates 6-DOF grasps from a single RGB-D image of the target object, which is…
Robotic grasping is one of the most fundamental robotic manipulation tasks and has been the subject of extensive research. However, swiftly teaching a robot to grasp a novel target object in clutter remains challenging. This paper attempts…
We present a follow-up study on our unified visuomotor neural model for the robotic tasks of identifying, localizing, and grasping a target object in a scene with multiple objects. Our Retinanet-based model enables end-to-end training of…
Mitigating catastrophic forgetting is a key hurdle in continual learning. Deep Generative Replay (GR) provides techniques focused on generating samples from prior tasks to enhance the model's memory capabilities using generative AI models…
A deep learning architecture is proposed to predict graspable locations for robotic manipulation. It considers situations where no, one, or multiple object(s) are seen. By defining the learning problem to be classification with null…
Robotic grasping is facing a variety of real-world uncertainties caused by non-static object states, unknown object properties, and cluttered object arrangements. The difficulty of grasping increases with the presence of more uncertainties,…
Grasping is a complex process involving knowledge of the object, the surroundings, and of oneself. While humans are able to integrate and process all of the sensory information required for performing this task, equipping machines with this…
As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments,it is…
As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are essential to operate…
Continual acquisition of novel experience without interfering previously learned knowledge, i.e. continual learning, is critical for artificial neural networks, but limited by catastrophic forgetting. A neural network adjusts its parameters…
Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously…
The comprehensive representation and understanding of the driving environment is crucial to improve the safety and reliability of autonomous vehicles. In this paper, we present a new approach to establish an environment model containing a…
The problem of catastrophic forgetting occurs in deep learning models trained on multiple databases in a sequential manner. Recently, generative replay mechanisms (GRM), have been proposed to reproduce previously learned knowledge aiming to…
The visual recognition of transitive actions comprising human-object interactions is a key component for artificial systems operating in natural environments. This challenging task requires jointly the recognition of articulated body…
Grasp detection in clutter requires the robot to reason about the 3D scene from incomplete and noisy perception. In this work, we draw insight that 3D reconstruction and grasp learning are two intimately connected tasks, both of which…
Being able to grasp objects is a fundamental component of most robotic manipulation systems. In this paper, we present a new approach to simultaneously reconstruct a mesh and a dense grasp quality map of an object from a depth image. At the…
Graph data in real-world scenarios undergo rapid and frequent changes, making it challenging for existing graph models to effectively handle the continuous influx of new data and accommodate data withdrawal requests. The approach to…
Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…