Imitation Learning

A study of human-like autonomous driving controllers in a driving simulator just got published in Transportation Research Part F: Traffic Psychology and Behavior. The article is written by Flavia Sofia Acerbo, the industrial PhD at Siemens and KU Leuven

In recent months, I’ve had the great honor of serving on PhD Defense Juries of four PhDs:

Driving from Vision through Differentiable Optimal Control

A great pleasure to have our two research engineers going to present the company Siemens Digital Industries Software R&D activities on human-centric AI in IEEE IROS and InCabin conferences this month.

Pleasure to have Siemens and our activities on autonomous driving being shown in the L4DC conference

Getting more insights of human driving preferences (i.e. when and how to brake, steering at different traffic scenarios), perceived safety, different cultures and styles,... are essential to improve ADAS control development

1. Reinforcement Learning from Simulation to Real World; 2. MPC-Based Imitation Learning for Human-Like Autonomous Driving; 3. Critical Driving Behaviours Using Driver's Risk Field

Data-driven control: advanced optimal control, imitation learning, driver behavior models, reinforcement learning

Learning from human driving demonstration is an interesting approach to improve autonomous driving policy. Still, it has some challenges: 1. majority logged data is from normal traffic situations, not sufficient critical and diverse scenarios data; and 2. during training and validation, the other traffic actors do not react to the ego's car policy, or no actual closed-loop response.

This paper draft is a nice piece of writing with quite some works, discussions, demonstrations, and evaluations on different learning methods.

The industrial PhD of Flavia is tackling some very interesting research, and this nice Award apparently shows a concrete progress. The work will also be presented at ICML (International Conference on Machine Learning) next week in Baltimore.

An interesting interview on the topic of ADAS comfort, made by Siemens Simcenter Engineering with our ADAS research engineer, Flavia.

We present the development and deployment of an embedded optimal control strategy for autonomous driving applications on a Ford Focus road vehicle.Non-linear model predictive control (NMPC) is designed and deployed on a system with hard real-time constraints. We show the properties of sequential quadratic programming (SQP) optimization solvers that are suitable for driving tasks

In the last few months, we have made some more progress to tackle some autonomous driving challenges in industry.

Several interesting advanced control technologies will be discussed there: MPC, combined model-based and AI or data learning from both human data or model learning, reinforcement learning, drift parking control, truck crossing roundabout with a failed steering, handling in snowy weather, virtual sensing, verification of NN, and also XiL testing

With the CCTA accepted paper, we are happy to be involved and show our innovative solutions in the recent four largest events of IFAC and IEEE Control System Society.