Understanding the dynamics of unknown object is crucial for collaborative robots including humanoids to more safely and accurately interact with humans. Most relevant literature leverage a force/torque sensor, prior knowledge of object, vision system, and a long-horizon trajectory which are often impractical. Moreover, these methods often entail solving non-linear optimization problem, sometimes yielding physically inconsistent results. In this work, we propose a fast learningbased inertial parameter estimation as more practical manner. We acquire a reliable dataset in a high-fidelity simulation and train a time-series data-driven regression model (e.g., LSTM) to estimate the inertial parameter of unknown objects. We also introduce a novel sim-to-real adaptation method combining Robot System Identification and Gaussian Processes to directly transfer the trained model to real-world application. We demonstrate our method with a 4-DOF single manipulator of physical wheeled humanoid robot, SATYRR. Results show that our method can identify the inertial parameters of various unknown objects faster and more accurately than conventional methods.
相關內容
State-of-the-art object detection methods applied to satellite and drone imagery largely fail to identify small and dense objects. One reason is the high variability of content in the overhead imagery due to the terrestrial region captured and the high variability of acquisition conditions. Another reason is that the number and size of objects in aerial imagery are very different than in the consumer data. In this work, we propose a small object detection pipeline that improves the feature extraction process by spatial pyramid pooling, cross-stage partial networks, heatmap-based region proposal network, and object localization and identification through a novel image difficulty score that adapts the overall focal loss measure based on the image difficulty. Next, we propose novel contrastive learning with progressive domain adaptation to produce domain-invariant features across aerial datasets using local and global components. We show we can alleviate the degradation of object identification in previously unseen datasets. We create a first-ever domain adaptation benchmark using contrastive learning for the object detection task in highly imbalanced satellite datasets with significant domain gaps and dominant small objects. The proposed method results in a 7.4% increase in mAP performance measure over the best state-of-art.
A robot in a human-centric environment needs to account for the human's intent and future motion in its task and motion planning to ensure safe and effective operation. This requires symbolic reasoning about probable future actions and the ability to tie these actions to specific locations in the physical environment. While one can train behavioral models capable of predicting human motion from past activities, this approach requires large amounts of data to achieve acceptable long-horizon predictions. More importantly, the resulting models are constrained to specific data formats and modalities. Moreover, connecting predictions from such models to the environment at hand to ensure the applicability of these predictions is an unsolved problem. We present a system that utilizes a Large Language Model (LLM) to infer a human's next actions from a range of modalities without fine-tuning. A novel aspect of our system that is critical to robotics applications is that it links the predicted actions to specific locations in a semantic map of the environment. Our method leverages the fact that LLMs, trained on a vast corpus of text describing typical human behaviors, encode substantial world knowledge, including probable sequences of human actions and activities. We demonstrate how these localized activity predictions can be incorporated in a human-aware task planner for an assistive robot to reduce the occurrences of undesirable human-robot interactions by 29.2% on average.
Privacy is a central challenge for systems that learn from sensitive data sets, especially when a system's outputs must be continuously updated to reflect changing data. We consider the achievable error for differentially private continual release of a basic statistic -- the number of distinct items -- in a stream where items may be both inserted and deleted (the turnstile model). With only insertions, existing algorithms have additive error just polylogarithmic in the length of the stream $T$. We uncover a much richer landscape in the turnstile model, even without considering memory restrictions. We show that every differentially private mechanism that handles insertions and deletions has worst-case additive error at least $T^{1/4}$ even under a relatively weak, event-level privacy definition. Then, we identify a parameter of the input stream, its maximum flippancy, that is low for natural data streams and for which we give tight parameterized error guarantees. Specifically, the maximum flippancy is the largest number of times that the contribution of a single item to the distinct elements count changes over the course of the stream. We present an item-level differentially private mechanism that, for all turnstile streams with maximum flippancy $w$, continually outputs the number of distinct elements with an $O(\sqrt{w} \cdot poly\log T)$ additive error, without requiring prior knowledge of $w$. We prove that this is the best achievable error bound that depends only on $w$, for a large range of values of $w$. When $w$ is small, the error of our mechanism is similar to the polylogarithmic in $T$ error in the insertion-only setting, bypassing the hardness in the turnstile model.
Human-robot interaction (HRI) research is progressively addressing multi-party scenarios, where a robot interacts with more than one human user at the same time. Conversely, research is still at an early stage for human-robot collaboration. The use of machine learning techniques to handle such type of collaboration requires data that are less feasible to produce than in a typical HRC setup. This work outlines scenarios of concurrent tasks for non-dyadic HRC applications. Based upon these concepts, this study also proposes an alternative way of gathering data regarding multi-user activity, by collecting data related to single users and merging them in post-processing, to reduce the effort involved in producing recordings of pair settings. To validate this statement, 3D skeleton poses of activity of single users were collected and merged in pairs. After this, such datapoints were used to separately train a long short-term memory (LSTM) network and a variational autoencoder (VAE) composed of spatio-temporal graph convolutional networks (STGCN) to recognise the joint activities of the pairs of people. The results showed that it is possible to make use of data collected in this way for pair HRC settings and get similar performances compared to using training data regarding groups of users recorded under the same settings, relieving from the technical difficulties involved in producing these data. The related code and collected data are publicly available.
Most existing locomotion devices that represent the sensation of walking target a user who is actually performing a walking motion. Here, we attempted to represent the walking sensation, especially a kinesthetic sensation and advancing feeling (the sense of moving forward) while the user remains seated. To represent the walking sensation using a relatively simple device, we focused on the force rendering and its evaluation of the longitudinal friction force applied on the sole during walking. Based on the measurement of the friction force applied on the sole during actual walking, we developed a novel friction force display that can present the friction force without the influence of body weight. Using performance evaluation testing, we found that the proposed method can stably and rapidly display friction force. Also, we developed a virtual reality (VR) walk-through system that is able to present the friction force through the proposed device according to the avatar's walking motion in a virtual world. By evaluating the realism, we found that the proposed device can represent a more realistic advancing feeling than vibration feedback.
Finding synthetic artifacts of spoofing data will help the anti-spoofing countermeasures (CMs) system discriminate between spoofed and real speech. The Conformer combines the best of convolutional neural network and the Transformer, allowing it to aggregate global and local information. This may benefit the CM system to capture the synthetic artifacts hidden both locally and globally. In this paper, we present the transfer learning based MFA-Conformer structure for CM systems. By pre-training the Conformer encoder with different tasks, the robustness of the CM system is enhanced. The proposed method is evaluated on both Chinese and English spoofing detection databases. In the FAD clean set, proposed method achieves an EER of 0.04%, which dramatically outperforms the baseline. Our system is also comparable to the pre-training methods base on Wav2Vec 2.0. Moreover, we also provide a detailed analysis of the robustness of different models.
Foundation models (FoMos), referring to large-scale AI models, possess human-like capabilities and are able to perform competitively in the domain of human intelligence. The breakthrough in FoMos has inspired researchers to deploy such models in the sixth-generation (6G) mobile networks for automating a broad range of tasks in next-generation mobile applications. While the sizes of FoMos are reaching their peaks, their next phase is expected to focus on fine-tuning the models to specific downstream tasks. This inspires us to propose the vision of FoMo fine-tuning as a 6G service. Its key feature is the exploitation of existing parameter-efficient fine-tuning (PEFT) techniques to tweak only a small fraction of model weights for a FoMo to become customized for a specific task. To materialize the said vision, we survey the state-of-the-art PEFT and then present a novel device-edge fine-tuning (DEFT) framework for providing efficient and privacy-preserving fine-tuning services at the 6G network edge. The framework consists of the following comprehensive set of techniques: 1) Control of fine-tuning parameter sizes in different transformer blocks of a FoMo; 2) Over-the-air computation for realizing neural connections in DEFT; 3) Federated DEFT in a multi-device system by downloading a FoMo emulator or gradients; 4) On-the-fly prompt-ensemble tuning; 5) Device-to-device prompt transfer among devices. Experiments are conducted using pre-trained FoMos with up to 11 billion parameters to demonstrate the effectiveness of DEFT techniques. The article is concluded by presenting future research opportunities.
An important prerequisite for autonomous robots is their ability to reliably grasp a wide variety of objects. Most state-of-the-art systems employ specialized or simple end-effectors, such as two-jaw grippers, which severely limit the range of objects to manipulate. Additionally, they conventionally require a structured and fully predictable environment while the vast majority of our world is complex, unstructured, and dynamic. This paper presents an implementation to overcome both issues. Firstly, the integration of a five-finger hand enhances the variety of possible grasps and manipulable objects. This kinematically complex end-effector is controlled by a deep learning based generative grasping network. The required virtual model of the unknown target object is iteratively completed by processing visual sensor data. Secondly, this visual feedback is employed to realize closed-loop servo control which compensates for external disturbances. Our experiments on real hardware confirm the system's capability to reliably grasp unknown dynamic target objects without a priori knowledge of their trajectories. To the best of our knowledge, this is the first method to achieve dynamic multi-fingered grasping for unknown objects. A video of the experiments is available at //youtu.be/Ut28yM1gnvI.
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on the ImageNet classification task has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are critical for their success? To answer these questions, we introduce a new Full Reference Image Quality Assessment (FR-IQA) dataset of perceptual human judgments, orders of magnitude larger than previous datasets. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by huge margins. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.
Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191