Recently, infrared small target detection (IRSTD) has been dominated by deep-learning-based methods. However, these methods mainly focus on the design of complex model structures to extract discriminative features, leaving the loss functions for IRSTD under-explored. For example, the widely used Intersection over Union (IoU) and Dice losses lack sensitivity to the scales and locations of targets, limiting the detection performance of detectors. In this paper, we focus on boosting detection performance with a more effective loss but a simpler model structure. Specifically, we first propose a novel Scale and Location Sensitive (SLS) loss to handle the limitations of existing losses: 1) for scale sensitivity, we compute a weight for the IoU loss based on target scales to help the detector distinguish targets with different scales: 2) for location sensitivity, we introduce a penalty term based on the center points of targets to help the detector localize targets more precisely. Then, we design a simple Multi-Scale Head to the plain U-Net (MSHNet). By applying SLS loss to each scale of the predictions, our MSHNet outperforms existing state-of-the-art methods by a large margin. In addition, the detection performance of existing detectors can be further improved when trained with our SLS loss, demonstrating the effectiveness and generalization of our SLS loss. The code is available at https://github.com/ying-fu/MSHNet.
Vision-language navigation (VLN) requires an agent to navigate through an 3D environment based on visual observations and natural language instructions. It is clear that the pivotal factor for successful navigation lies in the comprehensive scene understanding. Previous VLN agents employ monocular frameworks to extract 2D features of perspective views directly. Though straightforward, they struggle for capturing 3D geometry and semantics, leading to a partial and incomplete environment representation. To achieve a comprehensive 3D representation with fine-grained details, we introduce a Volumetric Environment Representation (VER), which voxelizes the physical world into structured 3D cells. For each cell, VER aggregates multi-view 2D features into such a unified 3D space via 2D-3D sampling. Through coarse-to-fine feature extraction and multi-task learning for VER, our agent predicts 3D occupancy, 3D room layout, and 3D bounding boxes jointly. Based on online collected VERs, our agent performs volume state estimation and builds episodic memory for predicting the next step. Experimental results show our environment representations from multi-task learning lead to evident performance gains on VLN. Our model achieves state-of-the-art performance across VLN benchmarks (R2R, REVERIE, and R4R).
In this study, we introduce a novel visual imitation network with a spatial attention module for robotic assisted feeding (RAF). The goal is to acquire (i.e., scoop) food items from a bowl. However, achieving robust and adaptive food manipulation is particularly challenging. To deal with this, we propose a framework that integrates visual perception with imitation learning to enable the robot to handle diverse scenarios during scooping. Our approach, named AVIL (adaptive visual imitation learning), exhibits adaptability and robustness across different bowl configurations in terms of material, size, and position, as well as diverse food types including granular, semi-solid, and liquid, even in the presence of distractors. We validate the effectiveness of our approach by conducting experiments on a real robot. We also compare its performance with a baseline. The results demonstrate improvement over the baseline across all scenarios, with an enhancement of up to 2.5 times in terms of a success metric. Notably, our model, trained solely on data from a transparent glass bowl containing granular cereals, showcases generalization ability when tested zero-shot on other bowl configurations with different types of food.
Robotic Assisted Feeding (RAF) addresses the fundamental need for individuals with mobility impairments to regain autonomy in feeding themselves. The goal of RAF is to use a robot arm to acquire and transfer food to individuals from the table. Existing RAF methods primarily focus on solid foods, leaving a gap in manipulation strategies for semi-solid and deformable foods. This study introduces Long-horizon Visual Action (LAVA) based food acquisition of liquid, semisolid, and deformable foods. Long-horizon refers to the goal of "clearing the bowl" by sequentially acquiring the food from the bowl. LAVA employs a hierarchical policy for long-horizon food acquisition tasks. The framework uses high-level policy to determine primitives by leveraging ScoopNet. At the mid-level, LAVA finds parameters for primitives using vision. To carry out sequential plans in the real world, LAVA delegates action execution which is driven by Low-level policy that uses parameters received from mid-level policy and behavior cloning ensuring precise trajectory execution. We validate our approach on complex real-world acquisition trials involving granular, liquid, semisolid, and deformable food types along with fruit chunks and soup acquisition. Across 46 bowls, LAVA acquires much more efficiently than baselines with a success rate of 89 +/- 4% and generalizes across realistic plate variations such as different positions, varieties, and amount of food in the bowl. Code, datasets, videos, and supplementary materials can be found on our website.
Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face challenges in terms of iteration complexity and robustness. Risk-sensitive RL, which balances expected return and risk, has been explored for its potential to yield probabilistically robust policies, yet its iteration complexity analysis remains underexplored. In this study, we conduct a thorough iteration complexity analysis for the risk-sensitive policy gradient method, focusing on the REINFORCE algorithm and employing the exponential utility function. We obtain an iteration complexity of $\mathcal{O}(\epsilon^{-2})$ to reach an $\epsilon$-approximate first-order stationary point (FOSP). We investigate whether risk-sensitive algorithms can achieve better iteration complexity compared to their risk-neutral counterparts. Our theoretical analysis demonstrates that risk-sensitive REINFORCE can have a reduced number of iterations required for convergence. This leads to improved iteration complexity, as employing the exponential utility does not entail additional computation per iteration. We characterize the conditions under which risk-sensitive algorithms can achieve better iteration complexity. Our simulation results also validate that risk-averse cases can converge and stabilize more quickly after approximately half of the episodes compared to their risk-neutral counterparts.
As technological advancements continue to expand the capabilities of multi unmanned-aerial-vehicle systems (mUAV), human operators face challenges in scalability and efficiency due to the complex cognitive load and operations associated with motion adjustments and team coordination. Such cognitive demands limit the feasible size of mUAV teams and necessitate extensive operator training, impeding broader adoption. This paper developed a Hand Gesture Based Interactive Control (HGIC), a novel interface system that utilize computer vision techniques to intuitively translate hand gestures into modular commands for robot teaming. Through learning control models, these commands enable efficient and scalable mUAV motion control and adjustments. HGIC eliminates the need for specialized hardware and offers two key benefits: 1) Minimal training requirements through natural gestures; and 2) Enhanced scalability and efficiency via adaptable commands. By reducing the cognitive burden on operators, HGIC opens the door for more effective large-scale mUAV applications in complex, dynamic, and uncertain scenarios. HGIC will be open-sourced after the paper being published online for the research community, aiming to drive forward innovations in human-mUAV interactions.
Advanced by rich perception and precise execution, robots possess immense potential to provide professional and customized rehabilitation exercises for patients with mobility impairments caused by strokes. Autonomous robotic rehabilitation significantly reduces human workloads in the long and tedious rehabilitation process. However, training a rehabilitation robot is challenging due to the data scarcity issue. This challenge arises from privacy concerns (e.g., the risk of leaking private disease and identity information of patients) during clinical data access and usage. Data from various patients and hospitals cannot be shared for adequate robot training, further compromising rehabilitation safety and limiting implementation scopes. To address this challenge, this work developed a novel federated joint learning (FJL) method to jointly train robots across hospitals. FJL also adopted a long short-term memory network (LSTM)-Transformer learning mechanism to effectively explore the complex tempo-spatial relations among patient mobility conditions and robotic rehabilitation motions. To validate FJL's effectiveness in training a robot network, a clinic-simulation combined experiment was designed. Real rehabilitation exercise data from 200 patients with stroke diseases (upper limb hemiplegia, Parkinson's syndrome, and back pain syndrome) were adopted. Inversely driven by clinical data, 300,000 robotic rehabilitation guidances were simulated. FJL proved to be effective in joint rehabilitation learning, performing 20% - 30% better than baseline methods.
Foundation models have indeed made a profound impact on various fields, emerging as pivotal components that significantly shape the capabilities of intelligent systems. In the context of intelligent vehicles, leveraging the power of foundation models has proven to be transformative, offering notable advancements in visual understanding. Equipped with multi-modal and multi-task learning capabilities, multi-modal multi-task visual understanding foundation models (MM-VUFMs) effectively process and fuse data from diverse modalities and simultaneously handle various driving-related tasks with powerful adaptability, contributing to a more holistic understanding of the surrounding scene. In this survey, we present a systematic analysis of MM-VUFMs specifically designed for road scenes. Our objective is not only to provide a comprehensive overview of common practices, referring to task-specific models, unified multi-modal models, unified multi-task models, and foundation model prompting techniques, but also to highlight their advanced capabilities in diverse learning paradigms. These paradigms include open-world understanding, efficient transfer for road scenes, continual learning, interactive and generative capability. Moreover, we provide insights into key challenges and future trends, such as closed-loop driving systems, interpretability, embodied driving agents, and world models. To facilitate researchers in staying abreast of the latest developments in MM-VUFMs for road scenes, we have established a continuously updated repository at https://github.com/rolsheng/MM-VUFM4DS
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in their capabilities, face challenges like escalating costs and demand for high-end GPUs. Drawing analogies between large-model-as-a-service (LMaaS) and cloud database-as-a-service (DBaaS), we describe an AI-native computing paradigm that harnesses the power of both cloud-native technologies (e.g., multi-tenancy and serverless computing) and advanced machine learning runtime (e.g., batched LoRA inference). These joint efforts aim to optimize costs-of-goods-sold (COGS) and improve resource accessibility. The journey of merging these two domains is just at the beginning and we hope to stimulate future research and development in this area.
Keyframe extraction aims to sum up a video's semantics with the minimum number of its frames. This paper puts forward a Large Model based Sequential Keyframe Extraction for video summarization, dubbed LMSKE, which contains three stages as below. First, we use the large model "TransNetV21" to cut the video into consecutive shots, and employ the large model "CLIP2" to generate each frame's visual feature within each shot; Second, we develop an adaptive clustering algorithm to yield candidate keyframes for each shot, with each candidate keyframe locating nearest to a cluster center; Third, we further reduce the above candidate keyframes via redundancy elimination within each shot, and finally concatenate them in accordance with the sequence of shots as the final sequential keyframes. To evaluate LMSKE, we curate a benchmark dataset and conduct rich experiments, whose results exhibit that LMSKE performs much better than quite a few SOTA competitors with average F1 of 0.5311, average fidelity of 0.8141, and average compression ratio of 0.9922.