Refine
H-BRS Bibliography
- yes (9)
Departments, institutes and facilities
Document Type
- Conference Object (4)
- Preprint (4)
- Report (1)
Year of publication
- 2020 (9) (remove)
Has Fulltext
- no (9)
Keywords
- Automatic Short Answer Grading (2)
- Active Learning (1)
- BERT (1)
- Black-Box Optimization (1)
- Domestic Robots (1)
- ELMo (1)
- GPT (1)
- GPT-2 (1)
- Human-Centered Robotics (1)
- Hyper-parameter Tuning (1)
An essential measure of autonomy in assistive service robots is adaptivity to the various contexts of human-oriented tasks, which are subject to subtle variations in task parameters that determine optimal behaviour. In this work, we propose an apprenticeship learning approach to achieving context-aware action generalization on the task of robot-to-human object hand-over. The procedure combines learning from demonstration and reinforcement learning: a robot first imitates a demonstrator’s execution of the task and then learns contextualized variants of the demonstrated action through experience. We use dynamic movement primitives as compact motion representations, and a model-based C-REPS algorithm for learning policies that can specify hand-over position, conditioned on context variables. Policies are learned using simulated task executions, before transferring them to the robot and evaluating emergent behaviours. We additionally conduct a user study involving participants assuming different postures and receiving an object from a robot, which executes hand-overs by either imitating a demonstrated motion, or adapting its motion to hand-over positions suggested by the learned policy. The results confirm the hypothesized improvements in the robot’s perceived behaviour when it is context-aware and adaptive, and provide useful insights that can inform future developments.
Deep learning models are extensively used in various safety critical applications. Hence these models along with being accurate need to be highly reliable. One way of achieving this is by quantifying uncertainty. Bayesian methods for UQ have been extensively studied for Deep Learning models applied on images but have been less explored for 3D modalities such as point clouds often used for Robots and Autonomous Systems. In this work, we evaluate three uncertainty quantification methods namely Deep Ensembles, MC-Dropout and MC-DropConnect on the DarkNet21Seg 3D semantic segmentation model and comprehensively analyze the impact of various parameters such as number of models in ensembles or forward passes, and drop probability values, on task performance and uncertainty estimate quality. We find that Deep Ensembles outperforms other methods in both performance and uncertainty metrics. Deep ensembles outperform other methods by a margin of 2.4% in terms of mIOU, 1.3% in terms of accuracy, while providing reliable uncertainty for decision making.
When a robotic agent experiences a failure while acting in the world, it should be possible to discover why that failure has occurred, namely to diagnose the failure. In this paper, we argue that the diagnosability of robot actions, at least in a classical sense, is a feature that cannot be taken for granted since it strongly depends on the underlying action representation. We specifically define criteria that determine the diagnosability of robot actions. The diagnosability question is then analysed in the context of a handle manipulation action, such that we discuss two different representations of the action – a composite policy with a learned success model for the action parameters, and a neural network-based monolithic policy – both of which exist on different sides of the diagnosability spectrum. Through this comparison, we conclude that composite actions are more suited to explicit diagnosis, but representations with less prior knowledge are more flexible. This suggests that model learning may provide balance between flexibility and diagnosability; however, data-driven diagnosis methods also need to be enhanced in order to deal with the complexity of modern robots.
Object detectors have improved considerably in the last years by using advanced CNN architectures. However, many detector hyper-parameters are generally manually tuned, or they are used with values set by the detector authors. Automatic Hyper-parameter optimization has not been explored in improving CNN-based object detectors hyper-parameters. In this work, we propose the use of Black-box optimization methods to tune the prior/default box scales in Faster R-CNN and SSD, using Bayesian Optimization, SMAC, and CMA-ES. We show that by tuning the input image size and prior box anchor scale on Faster R-CNN mAP increases by 2% on PASCAL VOC 2007, and by 3% with SSD. On the COCO dataset with SSD there are mAP improvement in the medium and large objects, but mAP decreases by 1% in small objects. We also perform a regression analysis to find the significant hyper-parameters to tune.
Abschlussbericht zum BMBF-Fördervorhaben Enabling Infrastructure for HPC-Applications (EI-HPC)
(2020)
Grasp verification is advantageous for autonomous manipulation robots as they provide the feedback required for higher level planning components about successful task completion. However, a major obstacle in doing grasp verification is sensor selection. In this paper, we propose a vision based grasp verification system using machine vision cameras, with the verification problem formulated as an image classification task. Machine vision cameras consist of a camera and a processing unit capable of on-board deep learning inference. The inference in these low-power hardware are done near the data source, reducing the robot's dependence on a centralized server, leading to reduced latency, and improved reliability. Machine vision cameras provide the deep learning inference capabilities using different neural accelerators. Although, it is not clear from the documentation of these cameras what is the effect of these neural accelerators on performance metrics such as latency and throughput. To systematically benchmark these machine vision cameras, we propose a parameterized model generator that generates end to end models of Convolutional Neural Networks(CNN). Using these generated models we benchmark latency and throughput of two machine vision cameras, JeVois A33 and Sipeed Maix Bit. Our experiments demonstrate that the selected machine vision camera and the deep learning models can robustly verify grasp with 97% per frame accuracy.
Efficient and comprehensive assessment of students knowledge is an imperative task in any learning process. Short answer grading is one of the most successful methods in assessing the knowledge of students. Many supervised learning and deep learning approaches have been used to automate the task of short answer grading in the past. We investigate why assistive grading with active learning would be the next logical step in this task as there is no absolute ground truth answer for any question and the task is very subjective in nature. We present a fast and easy method to harness the power of active learning and natural language processing in assisting the task of grading short answer questions. A webbased GUI is designed and implemented to incorporate an interactive short answer grading system. The experiments show that active learning saves the time and effort of graders in assessment and reaches the performance of supervised learning with less amount of graded answers for training.
Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer Grading
(2020)
Automatic Short Answer Grading (ASAG) is the process of grading the student answers by computational approaches given a question and the desired answer. Previous works implemented the methods of concept mapping, facet mapping, and some used the conventional word embeddings for extracting semantic features. They extracted multiple features manually to train on the corresponding datasets. We use pretrained embeddings of the transfer learning models, ELMo, BERT, GPT, and GPT-2 to assess their efficiency on this task. We train with a single feature, cosine similarity, extracted from the embeddings of these models. We compare the RMSE scores and correlation measurements of the four models with previous works on Mohler dataset. Our work demonstrates that ELMo outperformed the other three models. We also, briefly describe the four transfer learning models and conclude with the possible causes of poor results of transfer learning models.