Control

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

AI Agents and Agentic AI are increasingly considered in engineering workflows, not just for coding, reasoning, but also to learn from historical data and enhance automation. The big question remains: what real added value do they bring to engineering practice, i.e how AI Agents helps to accelerate simulation modeling, control design, or MBSE processes.

As the robotics revolution accelerates, one of our key visions is to combine simulation with real world testing across all: from control systems to AI model development, to verification and validation (V&V)

Last week, I had the pleasure visiting the Oxford Control Group to give a seminar and exchange ideas with faculty members and students. It was also great to meet the PhD student Rory Halsall, whom we jointly supervise within the collaboration between UK Research and Innovation and Siemens :).

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

It is a pleasure working with Prof. Alisa Rupenyan-Vasileva and the Postdoc Gabriele Fadini (ZHAW Zurich University of Applied Sciences), who are actively investigating state of the art autocalibration of high-dimensional control parameters using a combination of Digital Twin technology and AI methods.

FYI, interesting PhD position on data-driven optimal control for Air Mobility and Battery Management in Oxford Control Group.

One often overlooked topic in control systems engineering is explainability. Control engineers are typically trained, through university or research, to design systems from the ground up, starting with physics-based modeling, model identification, stability analysis, control design, and then iterating with performance evaluation. This process provides engineers insight into the system, enabling intuitive for parameter calibration.

Nice joint research project that combines academic and industrial environments. You will work on state of art control technologies and some cool applications :).

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.

Autocalibration control technologies can drastically reduce time and cost for engineers when moving from simulation to real-world testing. The method is for wide range of applications, not only autonomous driving.

From my industrial PhD Jean-Pierre: Proud and honored to have won the Young Author Award at the 8th International Federation of Automatic Control Nonlinear Model Predictive (IFAC NMPC2024) conference, held in the prestigious city of Kyoto, Japan.

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

Data-driven control has become more popular recently, where measurement data is exploited to design higher performance controller, robust to uncertainties and change of environment.

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

Last week, I had the pleasure of visiting Oxford Control Group and deliver a seminar there. It was an excellent opportunity to meet and discuss with great researchers in control systems, data-driven, and safety-based optimization fields. I was also delighted to hear that our works have inspired some PhDs there on their research :) .

4-5 years ago we developed an intuition to deal with this challenge, learning from control barrier function (CBF) from legged robotics community.

The goal of this project is to enhance safety and comfort in autonomous driving. Altogether we are developing and advancing different ADAS technologies, i.e. data collection, processing, scenario extraction-generation, algorithms (AI, control), XiL testing (X = model, hardware, human), and validation using several autonomous vehicle platforms.

This picture shows a Digital Twin vehicle together with the real Red Bull F1 vehicle (that Siemens partnering with), that has been inspiring us on developing Digital Twin for ADAS, autonomous driving.

See following demo from Siemens research engineer Jean Pierre Allamaa, done within the EU ELO-X Marie Curie project and in collaboration with Prof. Toshiyuki Ohtsuka (Kyoto Univ.) during a secondment program.

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

It was exciting to welcome the MECO group from KU Leuven last Friday at Siemens Digital Industries Software in Leuven.

Glad to see quite some Digital Twin research activities from UK robotics and control peers in the workshop.

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.

It is a nice way to start the weekend after a busy week: Our ADAS R&D team just received notifications that 3 papers got accepted to IFAC World Congress - (probably the biggest event of the Control system society this year). A nice achievement of the team members.

Reinforcement learning (RL) has shown capabilities to deal with complex systems, including autonomous driving. However, most results are only in simulation or game environments as training/testing in real life is unsafe and expensive.

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.

This week we just organized a workshop in Leuven office for the Marie Curie ITN ELO-X supervisors and ESR fellows.

Happy to share some of our team recent works and results on multiple topics around autonomous driving technologies development, leveraged by digital twin. The works are on both physical vehicle testing and virtual validation, implemented by research engineers and industrial PhDs in Engineering Services ADAS at Siemens Digital Industries Software and collaborators.)

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

Today I got a great pleasure to be an invited industrial speaker to the students of the Automation and Control Engineering Program of Politecnico di Milano, one of the largest programs I know so far in the field (i.e. with more than 400 control engineering students). I was excited with the opportunity to share and inspire the students with Siemens Simcenter, Digital Twin and engineering technologies, in particular our team developing autonomous vehicle control and testing solutions. Thank you again Prof. Lorenzo Fagiano for the invitation!

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

We show a demo comparison for an autonomous lane change scenario, where the same vehicle control system was applied to two vehicle dynamics models

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

Testing and validation are big challenges in the autonomous vehicles driving industry. Your ADAS engineers keep developing new perception or control algorithms, but what is an efficient process starting from there to vehicle deployment?

The key is to optimize control actions over a prediction horizon, which is often short due to computation.

This is my third year serving in the control system society as Associate Editor for conferences like CDC and ACC. A small role but I find this editorial work is an interesting way to keep updated with (and learn from) latest developments regularly from academics, and at the same time provide my R&D industry visions to the community!

People actually wants more from autonomous car, be cautious but also aggressive when necessary, be able and flexible moving along the tradeoff curves until physical limitation.

Besides, a nice example of collaboration not only within the team engineers but also with Marketing dept., who captures well the main messages, on-site ADAS demos and put them in such illustrative video

Next challenge is having an efficient framework from simulation to physical testing to validate your designs. This demo shows an example of our team works on MPC control development.

If you are participating and interested in automotive & autonomous vehicle, please consider the automotive control session next Wednesday afternoon. I and Karl Berntorp will co-chair it, hopefully we would have some interesting discussions and chats there.

Vehicle dynamics is essential for autonomous driving, in both safety and comfort performance. We show how to build a high fidelity vehicle model via simulation and proving ground testing, then exploit it for a safety-critical autonomous double lane change optimal control (MPC) development. This is a great video, with interesting (autonomous) driving scenes. Hope you will enjoy!

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.

It is my great pleasure to be in the finalist of AutoSens Award in the Most Influential Research Category for the our R&D works on autonomous vehicle control developments!

A great pleasure to visit Automatic Control Laboratory (LA) and Prof. Colin Jones