Autonomous Behavior Selection For Self-driving Cars Using Probabilistic Logic Factored Markov Decision Processes

Avilés, Héctor; Negrete, Marco; Reyes, Alberto; Machucho, Rubén; Rivera, Karelly; de-la-Garza, Gloria; Petrilli, Alberto

doi:10.1080/08839514.2024.2304942

Cited by 2 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Somewhere in between symbolic and sub-symbolic models are probabilistic logic factored Markov decision processes (PL-fMDPs). These models represent a promising alternative for behavior selection due to their capacity to model stochastic decision problems through a comprenhensible knowledge representation based on logic-syntax (Avilés et al, 2022(Avilés et al, , 2024.…”

Section: Introductionmentioning

confidence: 99%

Comparing Probabilistic Logic Factored MDPs, CART and MLPs for Behavior Selection in Self-Driving Cars

Avilés,

Rodríguez,

Reyes

et al. 2024

Preprint

View full text Add to dashboard Cite

We present a comparative study of probabilistic logic factored Markov decision processes (PL-fMDPs), classification and regression trees (CART), and multilayer perceptrons (MLPs) for behavior selection in self-driving cars. While CART and MLPs are widely used in decision-making, PL-fMDPs have been recently proposed for autonomous behavior selection with promising results. We carried out three main tests to evaluate these models: (i) learning and testing with examples taken from a simulated self-driving vehicle in a race-like scenario, (ii) comparison with actions of human drivers, and (iii) navigation of a self-driving car in two adverse and unknown road scenarios. In the first and third tests, CART slightly outperformed MLPs, and both narrowly surpassed PL-fMDPs. However, PL-fMDPs showed noticeably better alignment with the decisions of human drivers in the second test, at the cost of increased learning and testing time. The results demonstrate the competitiveness of all three approaches, although the definitive superiority of any one model was not observed across all evaluation contexts. This reinforces the need to explore hybrid approaches that combine symbolic, probabilistic, and connectionist models to leverage their respective strengths and mitigate their limitations for autonomous driving in self-driving cars.

show abstract

Section: Introductionmentioning

confidence: 99%