End-to-end Learning Method for Self-Driving Cars with Trajectory Recovery Using a Path-following Function

Onishi, Tadashi; Motoyoshi, T.; Suga, Yuki; Mori, Hiroki; Ogata, Tsuya

doi:10.1109/ijcnn.2019.8852322

Cited by 18 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, target tasks are limited to motions designed by the experimenter. Research has been conducted on automatic driving that corrects the predicted trajectory of learningbased controller to the standard target trajectory [22]. Although Onishi et al [22] used a model-based controller for augmenting training data during learning, they did not discuss its performance in a real environment.…”

Section: A Combining Learning-and Model-based Methodsmentioning

confidence: 99%

“…Research has been conducted on automatic driving that corrects the predicted trajectory of learningbased controller to the standard target trajectory [22]. Although Onishi et al [22] used a model-based controller for augmenting training data during learning, they did not discuss its performance in a real environment. In the field of control engineering, methods for combining machine learning and conventional control techniques have been studied.…”

Section: A Combining Learning-and Model-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Undefined motion guarantee by using model-based controller and prediction of past motion trajectory from embedded dynamics in Recurrent Neural Network

2020

Self Cite

View full text Add to dashboard Cite

For robotic applications, the robots task performance and operation must be guaranteed. In usual robot control, achieving robustness to various tasks as well as controller stability is difficult. This is similar to the problem of the generalization performance of machine learning. Although deep learning is a promising approach to complex tasks that are difficult to achieve using a conventional model-based control method, guaranteeing the output result of the model is still difficult. In this study, we propose an approach to compensate for the undefined behavior in the learning-based control method by using a model-based controller. Our method switches between two controllers according to the internal representation of a recurrent neural network that established the dynamics of task behaviors. We applied our method to a real robot and performed an error-recovery operation. To evaluate our model, we designed a pick-place task, and induced external disturbances. We present results in simulation and on a real robot.

show abstract

Section: A Combining Learning-and Model-based Methodsmentioning

confidence: 99%

Section: A Combining Learning-and Model-based Methodsmentioning

confidence: 99%

Undefined motion guarantee by using model-based controller and prediction of past motion trajectory from embedded dynamics in Recurrent Neural Network

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…As one of the machine learning technologies, imitation learning, which learns end-to-end mapping from observations to actions (i.e. steering, accelerating, and braking), is mainly utilized with a huge driving dataset [5,6,7]. In this study, we focus on such an imitation learning technology, which is simpler and more versatile, although its limitations about scalability were reported [8].…”

Section: Introductionmentioning

confidence: 99%

“…A research group of Sugiyama has developed quality-aware imitation learning methods [13,14], which estimate the quality of each data to select ones to be optimized. However, unlike behavioral cloning [15], which is often used in autonomous driving to learn the direct mapping from observations to actions [5,6,7], these methods are classified as inverse re-inforcement learning [16], which uses reinforcement learning [17] in combination and requires some trial and error by a non-optimal controller. R-MaxEnt also estimates the quality of each data through maximum entropy principle [18].…”

Section: Introductionmentioning

confidence: 99%

Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning

Kobayashi

Enomoto²

2021

Preprint

View full text Add to dashboard Cite

Autonomous driving has made great progress and been introduced in practical use step by step. On the other hand, the concept of personal mobility is also getting popular, and its autonomous driving specialized for individual drivers is expected for a new step. However, it is difficult to collect a large driving dataset, which is basically required for the learning of autonomous driving, from the individual driver of the personal mobility. In addition, when the driver is not familiar with the operation of the personal mobility, the dataset will contain non-optimal data. This study therefore focuses on an autonomous driving method for the personal mobility with such a small and noisy, so-called personal, dataset. Specifically, we introduce a new loss function based on Tsallis statistics that weights gradients depending on the original loss function and allows us to exclude noisy data in the optimization phase. In addition, we improve the visualization technique to verify whether the driver and the controller have the same region of interest. From the experimental results, we found that the conventional autonomous driving failed to drive properly due to the wrong operations in the personal dataset, and the region of interest was different from that of the driver. In contrast, the proposed method learned robustly against the errors and successfully drove automatically while paying attention to the similar region to the driver.

show abstract

“…Recent advancements in computer vision research on image classification, object detection, and object tracking enabled technological innovations in many industries including transportation [1], healthcare [2], and agriculture [3].…”

Section: Introductionmentioning

confidence: 99%

Towards in-store multi-person tracking using head detection and track heatmaps

Musaev¹,

Zhu²,

Cheng³

et al. 2020

Preprint

View full text Add to dashboard Cite

Computer vision algorithms are being implemented across a breadth of industries to enable technological innovations. In this paper, we study the problem of computer vision based customer tracking in retail industry. To this end, we introduce a dataset collected from a camera in an office environment where participants mimic various behaviors of customers in a supermarket. In addition, we describe an illustrative example of the use of this dataset for tracking participants based on a head tracking model in an effort to minimize errors due to occlusion. Furthermore, we propose a model for recognizing customers and staff based on their movement patterns. The model is evaluated using a realworld dataset collected in a supermarket over a 24-hour period that achieves 98% accuracy during training and 93% accuracy during evaluation.

show abstract

End-to-end Learning Method for Self-Driving Cars with Trajectory Recovery Using a Path-following Function

Cited by 18 publications

References 5 publications

Undefined motion guarantee by using model-based controller and prediction of past motion trajectory from embedded dynamics in Recurrent Neural Network

Undefined motion guarantee by using model-based controller and prediction of past motion trajectory from embedded dynamics in Recurrent Neural Network

Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning

Towards in-store multi-person tracking using head detection and track heatmaps

Contact Info

Product

Resources

About