Controlling Steering with Energy-Based Models

01/28/2023
by   Mykyta Baliesnyi, et al.
0

So-called implicit behavioral cloning with energy-based models has shown promising results in robotic manipulation tasks. We tested if the method's advantages carry on to controlling the steering of a real self-driving car with an end-to-end driving model. We performed an extensive comparison of the implicit behavioral cloning approach with explicit baseline approaches, all sharing the same neural network backbone architecture. Baseline explicit models were trained with regression (MAE) loss, classification loss (softmax and cross-entropy on a discretization), or as mixture density networks (MDN). While models using the energy-based formulation performed comparably to baseline approaches in terms of safety driver interventions, they had a higher whiteness measure, indicating higher jerk. To alleviate this, we show two methods that can be used to improve the smoothness of steering. We confirmed that energy-based models handle multimodalities slightly better than simple regression, but this did not translate to significantly better driving ability. We argue that the steering-only road-following task has too few multimodalities to benefit from energy-based models. This shows that applying implicit behavioral cloning to real-world tasks can be challenging, and further investigation is needed to bring out the theoretical advantages of energy-based models.

READ FULL TEXT

page 2

page 8

research
09/01/2021

Implicit Behavioral Cloning

We find that across a wide range of robot policy learning scenarios, tre...
research
03/27/2023

An active inference model of car following: Advantages and applications

Driver process models play a central role in the testing, verification, ...
research
07/12/2022

Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice

We present our findings in the gap between theory and practice of using ...
research
03/20/2019

Implicit Generation and Generalization in Energy-Based Models

Energy based models (EBMs) are appealing due to their generality and sim...
research
06/30/2022

LiDAR-as-Camera for End-to-End Driving

The core task of any autonomous driving system is to transform sensory i...
research
02/08/2023

Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation

Recent progress in end-to-end Imitation Learning approaches has shown pr...
research
06/02/2023

On Feature Diversity in Energy-based Models

Energy-based learning is a powerful learning paradigm that encapsulates ...

Please sign up or login with your details

Forgot password? Click here to reset