SimNet: Learning Reactive Self-driving Simulations from Real-world Observations

Bergamini, Luca; Ye, Yawei; Scheel, Oliver; Chen, Long; Hu, Chih Chi; Pero, Luca Del; Osiński, Błażej; Grimmett, Hugo; Ondrúška, Peter

doi:10.48550/arxiv.2105.12332

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human-like driving behavior models [62,7,57] are increasingly used to build realistic simulation for training self-driving vehicles, but they tend to suffer from excessive numbers of infractions, in particular collisions. In this experiment we take an existing model of human drivign behavior, ITRA [57], as the prior policy and attempt to avoid collisions, noting that CriticSMC is compatible with any probabilistic sequential behavior prediction model.…”

Section: Human-like Driving Behavior Modelingmentioning

confidence: 99%

“…Imitation of human driving behavior has been successfully used to learn control policies for autonomous vehicles [9,30] and more recently to generate realistic simulations [62,7,57]. In either case, a major concern is that those policies are significantly more likely than humans to perform driving infractions, of which collisions are the most salient.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Critic Sequential Monte Carlo

Lioutas¹,

Lavington²,

Sefas³

et al. 2022

Preprint

View full text Add to dashboard Cite

We introduce CriticSMC, a new algorithm for planning as inference built from a novel composition of sequential Monte Carlo with learned soft-Q function heuristic factors. This algorithm is structured so as to allow using large numbers of putative particles leading to efficient utilization of computational resource and effective discovery of high reward trajectories even in environments with difficult reward surfaces such as those arising from hard constraints. Relative to prior art our approach is notably still compatible with model-free reinforcement learning in the sense that the implicit policy we produce can be used at test time in the absence of a world model. Our experiments on self-driving car collision avoidance in simulation demonstrate improvements against baselines in terms of infraction minimization relative to computational effort while maintaining diversity and realism of found trajectories.

show abstract

Section: Human-like Driving Behavior Modelingmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Critic Sequential Monte Carlo

Lioutas¹,

Lavington²,

Sefas³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The current state-of-the-art function descriptor is generated by the self-learning function CNN [8]. SimNet [23] uses multiscale CNN [9] in a Siamese network [22] that learns 4096-dimensional embedding of images. Pairing is required for the Siamese network [22].…”

Section: Image Similarity With Deep Cnnmentioning

confidence: 99%

Identical Image Retrieval using Deep Learning

Nath¹,

Nayak²

2022

Preprint

View full text Add to dashboard Cite

In recent years, we know that the interaction with images has increased. Image similarity involves fetching similar-looking images abiding by a given reference image. The target is to find out whether the image searched as a query can result in similar pictures. We are using the BigTransfer Model, which is a state-of-art model itself. BigTransfer(BiT) is essentially a ResNet but pre-trained on a larger dataset like ImageNet and ImageNet-21k with additional modifications. Using the fine-tuned pre-trained Convolution Neural Network Model, we extract the key features and train on the K-Nearest Neighbor model to obtain the nearest neighbor. The application of our model is to find similar images, which are hard to achieve through text queries within a low inference time. We analyse the benchmark of our model based on this application.

show abstract

SimNet: Learning Reactive Self-driving Simulations from Real-world Observations

Cited by 2 publications

References 0 publications

Critic Sequential Monte Carlo

Critic Sequential Monte Carlo

Identical Image Retrieval using Deep Learning

Contact Info

Product

Resources

About