Are we done with object recognition? The iCub robot’s perspective

Pasquale, Giulia; Ciliberto, Carlo; Odone, Francesca; Rosasco, Lorenzo; Natale, Lorenzo

doi:10.1016/j.robot.2018.11.001

Cited by 40 publications

(22 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks have enabled state-of-the-art results in computer vision and are the natural first choice when building powerful perceptual systems for robots. Despite excellent results in constrained environments where sufficient training data can be precollected, deep learning approaches still fall short of addressing the needs of real-world robotic vision even for tasks such as object recognition that are commonly considered solved [134]. While today's neuromorphic technology might lower the power and latency of DNNs for certain visual inference tasks, new adaptive algorithms are needed that can cope with the full variability and unpredictability of the real world.…”

Section: Roboticsmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

View full text Add to dashboard Cite

Deep artificial neural networks apply principles of the brain's information processing that led to breakthroughs in machine learning spanning many problem domains. Neuromorphic computing aims to take this a step further to chips more directly inspired by the form and function of biological neural circuits, so they can process new knowledge, adapt, behave, and learn in real time at low power levels. Despite several decades of research, until recently, very few published results have shown that today's neuromorphic chips can demonstrate quantitative computational value. This is now changing with the advent of Intel's Loihi, a neuromorphic research processor designed to support a broad range of spiking neural networks with sufficient scale, performance, and features to deliver competitive results compared to state-of-the-art contemporary computing architectures. This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware. While conventional feedforward deep neural networks show modest if any benefit on Loihi, more brain-inspired networks using recurrence, precise spike-timing relationships, synaptic plasticity, stochasticity, and sparsity perform certain computation with orders of magnitude lower latency and energy compared to state-of-the-art conventional approaches. These compelling neuromorphic networks solve a diverse range of problems representative of brain-like computation, such as event-based

show abstract

Section: Roboticsmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The first dataset is the i C ub W orld28 dataset from Pasquale et al ( 2015a ) referred to as DS1 . It represents the visual perception of the iCub.…”

Section: Datasets and Methodsmentioning

confidence: 99%

“…One state-of-the-art visual recognition systems for incremental interactive object learning is provided by the iCub community. The approach utilizes a combination of a Deep Convolutional Neural Network (DCNN) for feature generation with a Multiclass Support Vector Machine (SVM) for classification of objects that were shown to the iCub (Pasquale et al, 2015a ). An exhaustive evaluation of the performance of the combined networks can be found in Sharif Razavian et al ( 2014 ).…”

Section: Introductionmentioning

confidence: 99%

On the Illumination Influence for Object Learning on Robot Companions

Keller

Lohan

2020

Front. Robot. AI

View full text Add to dashboard Cite

Most collaborative tasks require interaction with everyday objects (e.g., utensils while cooking). Thus, robots must perceive everyday objects in an effective and efficient way. This highlights the necessity of understanding environmental factors and their impact on visual perception, such as illumination changes throughout the day on robotic systems in the real world. In object recognition, two of these factors are changes due to illumination of the scene and differences in the sensors capturing it. In this paper, we will present data augmentations for object recognition that enhance a deep learning architecture. We will show how simple linear and non-linear illumination models and feature concatenation can be used to improve deep learning-based approaches. The aim of this work is to allow for more realistic Human-Robot Interaction scenarios with a small amount of training data in combination with incremental interactive object learning. This will benefit the interaction with the robot to maximize object learning for long-term and location-independent learning in unshaped environments. With our model-based analysis, we showed that changes in illumination affect recognition approaches that use Deep Convolutional Neural Network to encode features for object recognition. Using data augmentation, we were able to show that such a system can be modified toward a more robust recognition without retraining the network. Additionally, we have shown that using simple brightness change models can help to improve the recognition across all training set sizes.

show abstract

“…Commodities are detected and identified by image processing technology. Therefore, the detection and recognition of commodities has become a key part in a supermarket service robot [8,9]. Traditional methods of object detection and recognition are achieved by manually extracting hand-crafted features of objects, such as scale invariant feature transform (SIFT) [10,11], histograms of oriented gradients (HOG) [12], etc.…”

Section: Introductionmentioning

confidence: 99%

Designing a Supermarket Service Robot Based on Deep Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

In order to save people’s shopping time and reduce labor cost of supermarket operations, this paper proposes to design a supermarket service robot based on deep convolutional neural networks (DCNNs). Firstly, according to the shopping environment and needs of supermarket, the hardware and software structure of supermarket service robot is designed. The robot uses a robot operating system (ROS) middleware on Raspberry PI as a control kernel to implement wireless communication with customers and staff. So as to move flexibly, the omnidirectional wheels symmetrically installed under the robot chassis are adopted for tracking. The robot uses an infrared detection module to detect whether there are commodities in the warehouse or shelves or not, thereby grasping and placing commodities accurately. Secondly, the recently-developed single shot multibox detector (SSD), as a typical DCNN model, is employed to detect and identify objects. Finally, in order to verify robot performance, a supermarket environment is designed to simulate real-world scenario for experiments. Experimental results show that the designed supermarket service robot can automatically complete the procurement and replenishment of commodities well and present promising performance on commodity detection and recognition tasks.

show abstract

Are we done with object recognition? The iCub robot’s perspective

Cited by 40 publications

References 87 publications

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

On the Illumination Influence for Object Learning on Robot Companions

Designing a Supermarket Service Robot Based on Deep Convolutional Neural Networks

Contact Info

Product

Resources

About