The safety-critical nature of autonomous vehicle (AV) operation necessitates development of task-relevant algorithms that can reason about safety at the system level and not just at the component level. To reason about the impact of a perception failure on the entire system performance, such task-relevant algorithms must contend with various challenges: complexity of AV stacks, high uncertainty in the operating environments, and the need for real-time performance. To overcome these challenges, in this work, we introduce a Q-network called SPARQ (abbreviation for Safety evaluation for Perception And Recovery Q-network) that evaluates the safety of a plan generated by a planning algorithm, accounting for perception failures that the planning process may have overlooked. This Q-network can be queried during system runtime to assess whether a proposed plan is safe for execution or poses potential safety risks. If a violation is detected, the network can then recommend a corrective plan while accounting for the perceptual failure. We validate our algorithm using the NuPlan-Vegas dataset, demonstrating its ability to handle cases where a perception failure compromises a proposed plan while the corrective plan remains safe. We observe an overall accuracy and recall of 90% while sustaining a frequency of 42Hz on the unseen testing dataset. We compare our performance to a popular reachability-based baseline and analyze some interesting properties of our approach in improving the safety properties of an AV pipeline.
相關內容
The ability of intelligent systems to predict human behaviors is crucial, particularly in fields such as autonomous vehicle navigation and social robotics. However, the complexity of human motion have prevented the development of a standardized dataset for human motion prediction, thereby hindering the establishment of pre-trained models. In this paper, we address these limitations by integrating multiple datasets, encompassing both trajectory and 3D pose keypoints, to propose a pre-trained model for human motion prediction. We merge seven distinct datasets across varying modalities and standardize their formats. To facilitate multimodal pre-training, we introduce Multi-Transmotion, an innovative transformer-based model designed for cross-modality pre-training. Additionally, we present a novel masking strategy to capture rich representations. Our methodology demonstrates competitive performance across various datasets on several downstream tasks, including trajectory prediction in the NBA and JTA datasets, as well as pose prediction in the AMASS and 3DPW datasets. The code is publicly available: //github.com/vita-epfl/multi-transmotion
In Industry 4.0 systems, a considerable number of resource-constrained Industrial Internet of Things (IIoT) devices engage in frequent data interactions due to the necessity for model training, which gives rise to concerns pertaining to security and privacy. In order to address these challenges, this paper considers a digital twin (DT) and blockchain-assisted federated learning (FL) scheme. To facilitate the FL process, we initially employ fog devices with abundant computational capabilities to generate DT for resource-constrained edge devices, thereby aiding them in local training. Subsequently, we formulate an FL delay minimization problem for FL, which considers both of model transmission time and synchronization time, also incorporates cooperative jamming to ensure secure synchronization of DT. To address this non-convex optimization problem, we propose a decomposition algorithm. In particular, we introduce upper limits on the local device training delay and the effects of aggregation jamming as auxiliary variables, thereby transforming the problem into a convex optimization problem that can be decomposed for independent solution. Finally, a blockchain verification mechanism is employed to guarantee the integrity of the model uploading throughout the FL process and the identities of the participants. The final global model is obtained from the verified local and global models within the blockchain through the application of deep learning techniques. The efficacy of our proposed cooperative interference-based FL process has been verified through numerical analysis, which demonstrates that the integrated DT blockchain-assisted FL scheme significantly outperforms the benchmark schemes in terms of execution time, block optimization, and accuracy.
A safe and efficient decision-making system is crucial for autonomous vehicles. However, the complexity of driving environments limits the effectiveness of many rule-based and machine learning approaches. Reinforcement Learning (RL), with its robust self-learning capabilities and environmental adaptability, offers a promising solution to these challenges. Nevertheless, safety and efficiency concerns during training hinder its widespread application. To address these concerns, we propose a novel RL framework, Simple to Complex Collaborative Decision (S2CD). First, we rapidly train the teacher model in a lightweight simulation environment. In the more complex and realistic environment, teacher intervenes when the student agent exhibits suboptimal behavior by assessing actions' value to avert dangers. We also introduce an RL algorithm called Adaptive Clipping Proximal Policy Optimization Plus, which combines samples from both teacher and student policies and employs dynamic clipping strategies based on sample importance. This approach improves sample efficiency while effectively alleviating data imbalance. Additionally, we employ the Kullback-Leibler divergence as a policy constraint, transforming it into an unconstrained problem with the Lagrangian method to accelerate the student's learning. Finally, a gradual weaning strategy ensures that the student learns to explore independently over time, overcoming the teacher's limitations and maximizing performance. Simulation experiments in highway lane-change scenarios show that the S2CD framework enhances learning efficiency, reduces training costs, and significantly improves safety compared to state-of-the-art algorithms. This framework also ensures effective knowledge transfer between teacher and student models, even with suboptimal teachers, the student achieves superior performance, demonstrating the robustness and effectiveness of S2CD.
The increasing interest in autonomous driving systems has highlighted the need for an in-depth analysis of human driving behavior in diverse scenarios. Analyzing human data is crucial for developing autonomous systems that replicate safe driving practices and ensure seamless integration into human-dominated environments. This paper presents a comparative evaluation of human compliance with traffic and safety rules across multiple trajectory prediction datasets, including Argoverse 2, nuPlan, Lyft, and DeepUrban. By defining and leveraging existing safety and behavior-related metrics, such as time to collision, adherence to speed limits, and interactions with other traffic participants, we aim to provide a comprehensive understanding of each datasets strengths and limitations. Our analysis focuses on the distribution of data samples, identifying noise, outliers, and undesirable behaviors exhibited by human drivers in both the training and validation sets. The results underscore the need for applying robust filtering techniques to certain datasets due to high levels of noise and the presence of such undesirable behaviors.
A critical aspect of safe and efficient motion planning for autonomous vehicles (AVs) is to handle the complex and uncertain behavior of surrounding human-driven vehicles (HDVs). Despite intensive research on driver behavior prediction, existing approaches typically overlook the interactions between AVs and HDVs assuming that HDV trajectories are not affected by AV actions. To address this gap, we present a transformer-transfer learning-based interaction-aware trajectory predictor for safe motion planning of autonomous driving, focusing on a vehicle-to-vehicle (V2V) interaction scenario consisting of an AV and an HDV. Specifically, we construct a transformer-based interaction-aware trajectory predictor using widely available datasets of HDV trajectory data and further transfer the learned predictor using a small set of AV-HDV interaction data. Then, to better incorporate the proposed trajectory predictor into the motion planning module of AVs, we introduce an uncertainty quantification method to characterize the errors of the predictor, which are integrated into the path-planning process. Our experimental results demonstrate the value of explicitly considering interactions and handling uncertainties.
A common limitation of autonomous tissue manipulation in robotic minimally invasive surgery (MIS) is the absence of force sensing and control at the tool level. Recently, our team has developed miniature force-sensing forceps that can simultaneously measure the grasping and pulling forces during tissue manipulation. Based on this design, here we further present a method to automate tissue traction that comprises grasping and pulling stages. During this process, the grasping and pulling forces can be controlled either separately or simultaneously through force decoupling. The force controller is built upon a static model of tissue manipulation, considering the interaction between the force-sensing forceps and soft tissue. The efficacy of this force control approach is validated through a series of experiments comparing targeted, estimated, and actual reference forces. To verify the feasibility of the proposed method in surgical applications, various tissue resections are conducted on ex vivo tissues employing a dual-arm robotic setup. Finally, we discuss the benefits of multi-force control in tissue traction, evidenced through comparative analyses of various ex vivo tissue resections with and without the proposed method, and the potential generalization with traction on different tissues. The results affirm the feasibility of implementing automatic tissue traction using miniature forceps with multi-force control, suggesting its potential to promote autonomous MIS. A video demonstrating the experiments can be found at //youtu.be/f5gXuXe67Ak.
Autonomous vehicle (AV) motion planning problems often involve non-convex constraints, which present a major barrier to applying model predictive control (MPC) in real time on embedded hardware. This paper presents an approach for efficiently solving mixed-integer MPC motion planning problems using a hybrid zonotope representation of the obstacle-free space. The MPC optimization problem is formulated as a multi-stage mixed-integer quadratic program (MIQP) using a hybrid zonotope representation of the non-convex constraints. Risk-aware planning is supported by assigning costs to different regions of the obstacle-free space within the MPC cost function. A multi-stage MIQP solver is presented that exploits the structure of the hybrid zonotope constraints. For some hybrid zonotope representations, it is shown that the convex relaxation is tight, i.e., equal to the convex hull. In conjunction with logical constraints derived from the AV motion planning context, this property is leveraged to generate tight quadratic program (QP) sub-problems within a branch-and-bound mixed-integer solver. The hybrid zonotope structure is further leveraged to reduce the number of matrix factorizations that need to be computed within the QP sub-problems. Simulation studies are presented for obstacle-avoidance and risk-aware motion planning problems using polytopic maps and occupancy grids. In most cases, the proposed solver finds the optimal solution an order of magnitude faster than a state-of-the-art commercial solver. Processor-in-the-loop studies demonstrate the utility of the solver for real-time implementations on embedded hardware.
A wide variety of queueing systems can be naturally modeled as infinite-state Markov Decision Processes (MDPs). In the reinforcement learning (RL) context, a variety of algorithms have been developed to learn and optimize these MDPs. At the heart of many popular policy-gradient based learning algorithms, such as natural actor-critic, TRPO, and PPO, lies the Natural Policy Gradient (NPG) policy optimization algorithm. Convergence results for these RL algorithms rest on convergence results for the NPG algorithm. However, all existing results on the convergence of the NPG algorithm are limited to finite-state settings. We study a general class of queueing MDPs, and prove a $O(1/\sqrt{T})$ convergence rate for the NPG algorithm, if the NPG algorithm is initialized with the MaxWeight policy. This is the first convergence rate bound for the NPG algorithm for a general class of infinite-state average-reward MDPs. Moreover, our result applies to a beyond the queueing setting to any countably-infinite MDP satisfying certain mild structural assumptions, given a sufficiently good initial policy. Key to our result are state-dependent bounds on the relative value function achieved by the iterate policies of the NPG algorithm.
The rise of automation has provided an opportunity to achieve higher efficiency in manufacturing processes, yet it often compromises the flexibility required to promptly respond to evolving market needs and meet the demand for customization. Human-robot collaboration attempts to tackle these challenges by combining the strength and precision of machines with human ingenuity and perceptual understanding. In this paper, we conceptualize and propose an implementation framework for an autonomous, machine learning-based manipulator that incorporates human-in-the-loop principles and leverages Extended Reality (XR) to facilitate intuitive communication and programming between humans and robots. Furthermore, the conceptual framework foresees human involvement directly in the robot learning process, resulting in higher adaptability and task generalization. The paper highlights key technologies enabling the proposed framework, emphasizing the importance of developing the digital ecosystem as a whole. Additionally, we review the existent implementation approaches of XR in human-robot collaboration, showcasing diverse perspectives and methodologies. The challenges and future outlooks are discussed, delving into the major obstacles and potential research avenues of XR for more natural human-robot interaction and integration in the industrial landscape.
The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention based feature embedding that captures both entity and relation features in any given entity's neighborhood. Additionally, we also encapsulate relation clusters and multihop relations in our model. Our empirical study offers insights into the efficacy of our attention based model and we show marked performance gains in comparison to state of the art methods on all datasets.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191