Risk Assessment Algorithms Based on Recursive Neural Networks

Chinea, Alejandro; Parent, Michel

doi:10.1109/ijcnn.2007.4371169

Cited by 15 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This task provides an illustrative example of how an extremely complex problem is modeled using the recursive paradigm. Figure 4 provides a comparison of Back-propagation through the structure (Bpts), a quasi-Newton through the structure algorithm [21] (Qnts) and the proposed algorithm (Vets) running in batch mode. Graphics depict the result of averaging 10 simulations for two different network architectures.…”

Section: Resultsmentioning

confidence: 99%

Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity

Chinea

2009

Artificial Neural Networks – ICANN 2009

Self Cite

View full text Add to dashboard Cite

Recursive Neural Networks are non-linear adaptive models that are able to learn deep structured information. However, these models have not yet been broadly accepted. This fact is mainly due to its inherent complexity. In particular, not only for being extremely complex information processing models, but also because of a computational expensive learning phase. The most popular training method for these models is back-propagation through the structure. This algorithm has been revealed not to be the most appropriate for structured processing due to problems of convergence, while more sophisticated training methods enhance the speed of convergence at the expense of increasing significantly the computational cost. In this paper, we firstly perform an analysis of the underlying principles behind these models aimed at understanding their computational power. Secondly, we propose an approximate second order stochastic learning algorithm. The proposed algorithm dynamically adapts the learning rate throughout the training phase of the network without incurring excessively expensive computational effort. The algorithm operates in both on-line and batch modes. Furthermore, the resulting learning scheme is robust against the vanishing gradients problem. The advantages of the proposed algorithm are demonstrated with a real-world application example.

show abstract

Section: Resultsmentioning

confidence: 99%

Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity

Chinea

2009

Artificial Neural Networks – ICANN 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…These rule-based approaches ignore uncertainties of dynamic driving environments, leading to instabilities in their decisions. Second, risky situations can be determined by the similarity of a pattern between a pair of traffic participants with accident patterns obtained from accident databases [18], [19]. However, real-world accident data are hard to obtain.…”

Section: Related Workmentioning

confidence: 99%

DROID: Driver-centric Risk Object Identification

Li¹,

Chan²,

Chen³

2021

Preprint

View full text Add to dashboard Cite

A massive number of traffic fatalities are due to driver errors. To reduce fatalities, developing intelligent driving systems assisting drivers to identify potential risks is in urgent need. Risky situations are generally defined based on collision prediction in existing research. However, collisions are only one type of risk in traffic scenarios. We believe a more generic definition is required. In this work, we propose a novel driver-centric definition of risk, i.e., risky objects influence driver behavior. Based on this definition, a new task called risk object identification is introduced. We formulate the task as a cause-effect problem and present a novel two-stage risk object identification framework, taking inspiration from models of situation awareness and causal inference. A driver-centric Risk Object Identification (ROI) dataset is curated to evaluate the proposed system. We demonstrate state-of-the-art risk object identification performance compared with strong baselines on the ROI dataset. In addition, we conduct extensive ablative studies to justify our design choices.

show abstract

“…As an alternative, others have developed machine learning-based techniques to address a collision risk problem for autonomous vehicles. Chinea and Parent [11] attempted to assess the risk of a collision by training a Recursive Neural Network (RNN) from simulated driving data. In this work, risk is quantified in terms of the actions and objects present at road intersections including vehicles, pedestrians, buildings, etc.…”

Section: Related Workmentioning

confidence: 99%

Don’t Go That Way! Risk-Aware Decision Making for Autonomous Vehicles

2020

View full text Add to dashboard Cite

Risk is traditionally described as the expected likelihood of an undesirable outcome, such as collisions for autonomous vehicles. Accurately predicting risk or potentially risky situations is critical for the safe operation of autonomous vehicles. In our previous work, we showed that risk could be characterized by two components: 1) the probability of an undesirable outcome and 2) an estimate of how undesirable the outcome is (loss). This paper is an extension to our previous work. In this paper, using our trained deep reinforcement learning model for navigating around crowds, we developed a risk-based decision-making framework for the autonomous vehicle that integrates the high-level risk-based path planning with the reinforcement learning-based low-level control. We evaluated our method in a high-fidelity simulation such as CARLA. This work can improve safety by allowing an autonomous vehicle to one day avoid and react to risky situations.

show abstract

Risk Assessment Algorithms Based on Recursive Neural Networks

Cited by 15 publications

References 6 publications

Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity

Understanding the Principles of Recursive Neural Networks: A Generative Approach to Tackle Model Complexity

DROID: Driver-centric Risk Object Identification

Don’t Go That Way! Risk-Aware Decision Making for Autonomous Vehicles

Contact Info

Product

Resources

About