Energy efficient architecture is essential to improve both the performance and power consumption of a computer system. However, modern computers suffer from the severe “memory wall” problem due to the significant performance gap between the processor technology and the memory technology. Thus, the computer architecture community is evolving from compute-centric to memory-centric designs to reduce the data movement overhead. This paper presents a comprehensive survey of the main challenges and recent advances in memory-centric energy efficient computer architecture. We summarize two research directions: improving the memory technology and processing closer to memory. The former focuses on optimizing the conventional memory technology and exploiting emerging non-volatile memory (NVM) technology. The latter talks about currently popular processing in memory (PIM) technology, including near-memory processing (NMP) and in-memory processing (IMP). Moreover, some other topics like hardware for machine learning (ML), ML for hardware, security, privacy, and reliability are gaining increasing attention and should be considered seriously in the design phase of a computer system. The community is facing various challenges and opportunities simultaneously, requiring researchers to have a more comprehensive understanding of this field which is also the goal of this paper.

Artificial fish-like robot is an important branch of underwater robot research. At present, most of fish-like robot research focuses on single robot mechanism behavior, some research pays attention to the influence of the hydro-environment on robot crowds but does not reach a unified conclusion on the efficiency of fish-like robots swarm. In this work, the fish-like robots swarm is studied by numerical simulation. Four different formations, including the tandem, the phalanx, the diamond, and the rectangle are conducted by changing the spacing between fishes. The results show that at close spacing, the fish in the back can obtain a large wake from the front fish, but suffers large lateral power loss from the lateral fish. On the contrary, when the spacing is large, both the wake and pressure caused by the front and side fishes become small. In terms of the average swimming efficiency of fish swarms, we find that when the fish spacing is less than $1.25L$ (L is the length of the fish body), the tandem swarm is the best choice. When the spacing is $1.25L$ , the tandem, diamond and rectangle swarms have similar efficiency. When the spacing is larger than $1.25L$ , the rectangle swarm is more efficient than other formations. The findings will provide significant guidance for the control of fish-like robots swarm.

Autonomous Underwater Vehicle (AUV) has become a hotspot in the field of robot in recent years. As a special kind of AUV, the robotic fish can achieve better propulsion efficiency and maneuverability than traditional AUVs. Studies show that robotic fish formation can save energy and perform more complex tasks than single robotic fish, but it is difficult to maintain a stable formation because the nearby environmental condition is hard to obtain. Inspired by the lateral line system (LLS) of fish, this paper constructs a predictive model of flow velocity and a judgement model of spacing between individual platforms for robotic fish formation through monitoring sensors on robotic fish surface. The models are built by methods of polynomial fitting and neural networks based on Computational Fluid Dynamics (CFD) simulation. The results show that the flow velocity predicted by our model could reduce the error to $0.4\%$ , and the spacing judgement accuracy could reach at least 80%. The findings are useful for maintaining a stable formation and will provide significant guidance for the control of robotic fish formation and sensor installation position on the robotic fish surface.

Recently, the bottleneck of multi-object tracking is shifting from detection performance to association performance. However, research on association algorithms requires a large number of identity labels, which are more expensive than detection labels. To circumvent the need for identity labels, we propose a Self-supervised Re-identification module for online joint Multi-Object Tracking (SR-MOT). Specifically, we design an appearance discriminator to judge identities based solely on detection hypotheses and then associate the same identity with the final trajectory. To train the discriminator without using identity labels, we construct negative pairs by the detections that appear in the same video frame, as they definitely belong to different identities. Positive pairs are naturally constructed through several useful data augmentation strategies at the box level. In addition, our proposed method balances conflicting detection and re-ID tasks by using different output features and dynamically adjusts detection and re-ID loss weights based on the information content of the loss distribution to promote balance between the two tasks from the feature level and optimization methods. In our evaluation on the MOT Challenge benchmark, we show that our SR-MOT performs comparably to supervised methods and is significantly superior to other unsupervised methods. Our proposed method provides a practical solution for multi-object tracking without the need for identity labels, making it more accessible for real-world applications.

The rapid development of remote sensing technology has provided new sources of data for marine rescue and has made it possible to find and track survivors. Due to the requirement of tracking multiple survivors at the same time, multi-object tracking (MOT) has become the key subtask of marine rescue. However, there exists a significant gap between fine-grained objects in realistic marine rescue remote sensing data and the fine-grained object tracking capability of existing MOT technologies, which mainly focuses on coarse-grained object scenarios and fails to track fine-grained instances. Such a gap limits the practical application of MOT in realistic marine rescue remote sensing data, especially when rescue forces are limited. Given the promising fine-grained classification performance of recent text-guided methods, we delve into leveraging labels and attributes to narrow the gap between MOT and fine-grained maritime rescue. We propose a text-guided multi-class multi-object tracking (TG-MCMOT) method. To handle the problem raised by fine-grained classes, we design a multi-modal encoder by aligning external textual information with visual inputs. We use decoding information at different levels, simultaneously predicting the category, location, and identity embedding features of objects. Meanwhile, to improve the performance of small object detection, we also develop a data augmentation pipeline to generate pseudo-near-infrared images based on RGB images. Extensive experiments demonstrate that our TG-MCMOT not only performs well on typical metrics in the maritime rescue task (SeaDronesSee dataset), but it also effectively tracks open-set categories on the BURST dataset. Specifically, on the SeaDronesSee dataset, the Higher Order Tracking Accuracy (HOTA) reached a score of 58.8, and on the BURST test dataset, the HOTA score for the unknown class improved by 16.07 points.