For robots to attain more general-purpose utility, grasping is a necessary skill to master. Such general-purpose robots may use their perception abilities to visually identify grasps for a given object. A grasp describes how a robotic end-effector can be arranged to securely grab an object and successfully lift it without slippage. Traditionally, grasp detection requires expert human knowledge to analytically form the task-specific algorithm, but this is an arduous and time-consuming approach. During the last five years, deep learning methods have enabled significant advancements in robotic vision, natural language processing, and automated driving applications. The successful results of these methods have driven robotics researchers to explore the use of deep learning methods in task-generalised robotic applications. This paper reviews the current state-of-the-art in regards to the application of deep learning methods to generalised robotic grasping and discusses how each element of the deep learning approach has improved the overall performance of robotic grasp detection. Several of the most promising approaches are evaluated and the most suitable for real-time grasp detection is identified as the one-shot detection method. The availability of suitable volumes of appropriate training data is identified as a major obstacle for effective utilisation of the deep learning approaches, and the use of transfer learning techniques is proposed as a potential mechanism to address this. Finally, current trends in the field and future potential research directions are discussed.

The capabilities of autonomous mobile robotic systems have been steadily improving due to recent advancements in computer science, engineering, and related disciplines such as cognitive science. In controlled environments, robots have achieved relatively high levels of autonomy. In more unstructured environments, however, the development of fully autonomous mobile robots remains challenging due to the complexity of understanding these environments. Many autonomous mobile robots use classical, learning-based or hybrid approaches for navigation. More recent learning-based methods may replace the complete navigation pipeline or selected stages of the classical approach. For effective deployment, autonomous robots must understand their external environments at a sophisticated level according to their intended applications. Therefore, in addition to robot perception, scene analysis and higher-level scene understanding (e.g., traversable/non-traversable, rough or smooth terrain, etc.) are required for autonomous robot navigation in unstructured outdoor environments. This paper provides a comprehensive review and critical analysis of these methods in the context of their applications to the problems of robot perception and scene understanding in unstructured environments and the related problems of localisation, environment mapping and path planning. State-of-the-art sensor fusion methods and multimodal scene understanding approaches are also discussed and evaluated within this context. The paper concludes with an in-depth discussion regarding the current state of the autonomous ground robot navigation challenge in unstructured outdoor environments and the most promising future research directions to overcome these challenges.

Classification of human actions is an ongoing research problem in computer vision. This review is aimed to scope current literature on data fusion and action recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The increase in the number of action recognition datasets intersects with advances in deep learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality—such as RGB, depth, skeleton, and infrared (IR)—has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this paper, we focus solely on data fusion and recognition techniques in the context of vision with an RGB-D perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions.

Due to its widespread applications, human action recognition is one of the most widely studied research problems in Computer Vision. Recent studies have shown that addressing it using multimodal data leads to superior performance as compared to relying on a single data modality. During the adoption of deep learning for visual modelling in the past decade, action recognition approaches have mainly relied on Convolutional Neural Networks (CNNs). However, the recent rise of Transformers in visual modelling is now also causing a paradigm shift for the action recognition task. This survey captures this transition while focusing on Multimodal Human Action Recognition (MHAR). Unique to the induction of multimodal computational models is the process of ‘fusing’ the features of the individual data modalities. Hence, we specifically focus on the fusion design aspects of the MHAR approaches. We analyze the classic and emerging techniques in this regard, while also highlighting the popular trends in the adaption of CNN and Transformer building blocks for the overall problem. In particular, we emphasize on recent design choices that have led to more efficient MHAR models. Unlike existing reviews, which discuss Human Action Recognition from a broad perspective, this survey is specifically aimed at pushing the boundaries of MHAR research by identifying promising architectural and fusion design choices to train practicable models. We also provide an outlook of the multimodal datasets from their scale and evaluation viewpoint. Finally, building on the reviewed literature, we discuss the challenges and future avenues for MHAR.

Multimodal Human Action Recognition (MHAR) is an important research topic in computer vision and event recognition fields. In this work, we address the problem of MHAR by developing a novel audio-image and video fusion-based deep learning framework that we call Multimodal Audio-Image and Video Action Recognizer (MAiVAR). We extract temporal information using image representations of audio signals and spatial information from video modality with the help of Convolutional Neutral Networks (CNN)-based feature extractors and fuse these features to recognize respective action classes. We apply a high-level weights assignment algorithm for improving audio-visual interaction and convergence. This proposed fusion-based framework utilizes the influence of audio and video feature maps and uses them to classify an action. Compared with state-of-the-art audio-visual MHAR techniques, the proposed approach features a simpler yet more accurate and more generalizable architecture, one that performs better with different audio-image representations. The system achieves an accuracy 87.9% and 79.0% on UCF51 and Kinetics Sounds datasets, respectively. All code and models for this paper will be available at https://tinyurl.com/4ps2ux6n.