Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find...
详细信息
ISBN:
(纸本)9781728196817
Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find a path due to mischaracterizing deformable objects as rigid and impassable. Instead, we learn to predict an estimate of traversability of terrain regions and to prefer regions that are easier to navigate (e.g., short grass over small shrubs). Rather than predicting collisions, we instead regress on realized error compared to a canonical system model. We train with an on-policy approach, resulting in successful navigation policies using as little as 50 minutes of training data split across simulation and real world. Our learning-based navigation system is a sample efficient short-term planner that we demonstrate on a Clearpath Husky navigating through a variety of terrain including grassland and forest.
This paper discusses the design, construction, and characteristics of a holonomic drive-based multi-functional rehabilitation robot that caters to the therapeutic requirements of the upper and lower limb for stroke pa...
详细信息
Manipulators are used extensively in industrial and service sectors due to their capability to carry out a task effectively. This paper presents a kinematic modelling, a workspace analysis, a static structural analysi...
详细信息
ISBN:
(纸本)9798350373141;9798350373158
Manipulators are used extensively in industrial and service sectors due to their capability to carry out a task effectively. This paper presents a kinematic modelling, a workspace analysis, a static structural analysis and a simulation study of a simple 3 degrees-of-freedom (DoF) Cartesian manipulator developed for pressing buttons of an elevator. Denavit-Hartenberg approach was used for determining kinematic equations, which allowed constructing a manipulator workspace. A static structural analysis in ABAQUS determined stresses and deformations acting at manipulator links. The dimensions and material for fabricating the manipulator were selected using static structural analysis. Simulations with virtual human models from LIRS-HMLG library were carried out in Gazebo to study motion capabilities and range of the manipulator, and evaluate its performance in a human-robot interaction scenario.
This paper presents a vision-based selective spraying technique for an autonomous agricultural sprayer robot. In traditional methods, excessive chemical spraying cause deleterious effects on human health, environment ...
详细信息
A new method for the design of linear systems with desired poles and zeros of their transfer matrices is proposed. Conditions for the existence of the solution to the problem and the procedure for computation of the d...
详细信息
ISBN:
(数字)9798350362343
ISBN:
(纸本)9798350362350
A new method for the design of linear systems with desired poles and zeros of their transfer matrices is proposed. Conditions for the existence of the solution to the problem and the procedure for computation of the desired matrices are given. The procedure is illustrated by numerical simple examples.
Task planning capabilities are crucial for intelligent robots to operate autonomously in the physical world. However, traditional Planning Domain Definition Language (PDDL) based methods often suffer from combinatoria...
详细信息
Predicting object locations in everyday scenarios is critical for service robots performing tasks such as object search and planning. Previous knowledge reasoning methods mostly use object class for prediction while n...
详细信息
ISBN:
(数字)9789819607921
ISBN:
(纸本)9789819607914;9789819607921
Predicting object locations in everyday scenarios is critical for service robots performing tasks such as object search and planning. Previous knowledge reasoning methods mostly use object class for prediction while neglecting n-ary multimodal properties. In this paper, we introduce a novel Few-shot n-Ary Knowledge Inference framework, FAKI, aimed to infer target locations using large language models (LLMs). By integrating few-shot In-Context Learning (ICL) method, we select the top-k most similar samples using K-Nearest Neighbors (KNN) for contextual information. To solve incomplete observations in few-shot scenarios, we provide the Metainfo, which contains data distribution in the trainset as hints for LLM. Leveraging KNN and Metainfo, our method achieves state-of-the-art (SOTA) performance on the LINK dataset for location prediction, outperforming the previous SOTA by 17.6%. Furthermore, we investigate the effects of prompt design, ICL, and top-k selection on prediction accuracy, providing deeper insights in few-shot n-ary knowledge inference.
NDE 4.0 represents the integration of recent advancements in robotics, sensor technology, and Artificial Intelligence (AI), transforming and automating traditional NDE in line with Industry 4.0 principles. Despite the...
详细信息
NDE 4.0 represents the integration of recent advancements in robotics, sensor technology, and Artificial Intelligence (AI), transforming and automating traditional NDE in line with Industry 4.0 principles. Despite these advancements, data analysis in NDE is still largely performed manually or with traditional rule-based tools such as signal thresholding. These tools often struggle to effectively manage complex data patterns or high noise levels, leading to unreliable defect detection. Additionally, they require frequent manual adjustments to set appropriate parameters for varying inspection conditions, which can be inefficient and error-prone in dynamic or fast paced environments. In contrast, AI-based analysis tools have demonstrated improvements over traditional methods, offering greater accuracy in defect detection and adaptability to higher variability within captured signals. However, their adoption in industrial settings remains limited due to challenges associated with model trust and their "black box" nature. Additionally, practical guidelines for implementing AI tools into NDE workflow are rarely discussed, motivating this work to explore various integration strategies across different automation levels. Three levels of automation were explored, ranging from basic AI-assisted workflows, where tools provide suggestions, to advanced applications where multiple AI models simultaneously process data in a comprehensive analysis, shifting human operators to a supervisory role. Proposed strategies of AI integration into the NDE automation workflow were evaluated on inspection of two defective complex-geometry carbon fibrereinforced plastics components, commonly used in aerospace and energy sectors for safety-critical structures such as aircraft fuselages and wind turbine blades. The experimental scans were conducted using a phased array ultrasonic testing roller probe mounted on an industrial manipulator, closely replicating industrial practices, and successfully
Model Predictive Control (MPC) while being a very effective control technique can become computationally demanding when a large prediction horizon is selected. To make the problem more tractable, one technique that ha...
详细信息
ISBN:
(数字)9781665468589
ISBN:
(纸本)9781665468596;9781665468589
Model Predictive Control (MPC) while being a very effective control technique can become computationally demanding when a large prediction horizon is selected. To make the problem more tractable, one technique that has been proposed in the literature makes use of control input parameterizations to decrease the numerical complexity of nonlinear MPC problems without necessarily affecting the performances significantly. In this paper, we review the use of parameterizations and propose a simple Sequential Quadratic Programming algorithm for nonlinear MPC. We benchmark the performances of the solver in simulation and compare them with state-of-the-art solvers. Results show that parameterizations allow to attain good performances with (significantly) lower computation times.
In this paper, we propose a novel consistent state estimator design for visual-inertial systems. Motivated by first-estimates Jacobian (FEJ) based estimators - which uses the first-ever estimates as linearization poin...
详细信息
ISBN:
(纸本)9781728196817
In this paper, we propose a novel consistent state estimator design for visual-inertial systems. Motivated by first-estimates Jacobian (FEJ) based estimators - which uses the first-ever estimates as linearization points to preserve proper observability properties of the linearized estimator thereby improving the consistency - we carefully model measurement linearization errors due to its Jacobian evaluation and propose a methodology which still leverages FEJ to ensure the estimator's observability properties, but additionally explicitly compensate for linearization errors caused by poor first estimates. We term this estimator FEJ2, which directly addresses the discrepancy between the best Jacobian evaluated at the latest state estimate and the first-estimates Jacobian evaluated at the first-time-ever state estimate. We show that this process explicitly models that the FEJ used is imperfect and thus contributes additional error which, as in FEJ2, should be modeled and consistently increase the state covariance during update. The proposed FEJ2 is evaluated against state-of-the-art visual-inertial estimators in both Monte-Carlo simulations and real-world experiments, which has been shown to outperform existing methods and to robustly handle poor first estimates and high measurement noises.
暂无评论