Inscrivez-vous pour accéder à toutes les fonctionnalités de notre service.
  • Recherche d'offres d'emploi
  • Favoris
  • Créer un CV
    Nouveau
  • Salaires
  • Souscriptions

Learning to Perceive in Degraded Environments

Stage

imec

Intelligent systems operating in underwater environments, adverse weather, darkness, smoke, cluttered scenes, or under partial sensor failure must continuously determine not only what they can perceive, but also how they should acquire information in order to perceive effectively. This need to adapt how information is acquired and processed extends also across autonomous systems, industrial monitoring, automotive perception, and intelligent sensing platforms operating in dynamic real-world environments. In such settings, the value of information is highly context-dependent: the usefulness of a sensing modality, sensing configuration, or computational strategy may change over time, across locations, and according to the mission/task being performed. Existing research has made significant advances in robust perception, multimodal fusion, active sensing, and resource-aware AI. However, these areas have largely evolved independently, leaving a fundamental open question: which properties must a learned representation capture in order to predict the future usefulness, reliability, and cost of information under changing environmental and operational conditions, and thereby support improved perception decisions?

This PhD investigates the learning of effective and efficient representations for active multimodal perception in degraded and uncertain environments. The central hypothesis is that perception systems require an intermediate representation layer that captures not only what is observed, but also the latent factors that determine the expected value, reliability, and cost of future observations. Such representations should enable perception systems to estimate these quantities as environmental conditions and mission priorities evolve. This information can subsequently support decisions such as selecting sensing modalities, adapting sensing strategies, or allocating computational resources.

A key challenge is that these representations must simultaneously support multiple and often competing objectives. They must be informative enough to improve perception performance, compact enough to operate under constraints such as latency, energy consumption, bandwidth, battery life, and computational budgets, and robust across a range of sensing conditions and mission objectives. The research therefore focuses on learning representations that balance effectiveness and efficiency while remaining actionable for decision-making in resource-constrained systems.

An additional objective is to ensure that the learned representations expose the factors that underlie perception decisions (i.e., estimates of uncertainty, expected benefit, and resource implications), providing a deliberate layer of interpretable communication between perception and decision-making processes. Rather than treating perception decisions as opaque outputs, the research investigates how systems can communicate, in human-understandable terms, the trade-offs underlying their sensing choices. Such capabilities are increasingly important in safety-critical and long-duration deployments where operators must understand, trust, and audit autonomous behaviour.

Thus, this PhD research should be naturally structured around three hierarchical pillars:

Learning representations of information value: The primary focus is to understand which properties a learned representation must capture in order to predict the reliability and cost of information under changing environmental conditions, mission objectives, and resource constraints. This research explores new directions in representation learning, uncertainty modelling, and multimodal AI, supported by large-scale experiments in realistic simulation and physics-based digital worlds.

Guiding active multimodal perception: Building on these representations, the research investigates how they can support sensing and computation decisions, enabling systems to adapt how information is acquired and processed in response to uncertainty, operational context, and available resources. The resulting algorithms will be trained, tested, and demonstrated in realistic digital worlds combining robotics, physics-based rendering, and multimodal sensor simulation, before being transferred to real-world experimental platforms.

Bridging perception and auditable AI reasoning: Finally, the research explores how learned representations can become a semantic interface between sensing systems and next-generation AI models, allowing autonomous agents to reason about uncertainty, information value, and resource costs when deciding how to perceive and act.

The resulting scientific framework aims to provide a principled basis for learning representations that guide perception decisions under uncertainty and resource constraints in a principled, auditable way. By linking representation learning with active multimodal perception, the research seeks to advance the development of more adaptive and trustworthy sensing systems that respond effectively to the complexity of real-world environments. This is a strong outcome towards the broad adoption of autonomous, intelligent systems and should actively contribute to the maturity and scalability of imec’s next generation sensing and perception systems.

Our ideal candidate for this position has the following skills:

You have a Master’s degree in AI, Computer Science, Electrical Engineering, Robotics, Applied Mathematics, or a related field.

You have solid knowledge of machine learning and deep learning, with an interest in representation learning, multimodal perception, and embedded or resource-aware AI.

You are interested in designing algorithms that enable intelligent systems to adapt how they acquire and process sensor information.

You have good programming skills and are flexible in using software tools and machine-learning frameworks such as Git, PyTorch, or TensorFlow.

Experience with multimodal sensor data, sensor fusion, active sensing, robotics, or autonomous systems is considered a plus.

Understanding the properties and limitations of different sensor modalities is considered a plus.

Experience with uncertainty estimation or resource-constrained machine learning is considered a plus.

You can plan and carry out research tasks independently while contributing effectively to a multidisciplinary team.

You have strong analytical skills and can critically interpret, communicate, and document research results.

You are responsible, curious, communicative, and flexible, with a willingness to work across application domains.

Your English is fluent, both spoken and written.

As a joint imec-VUB AI Lab PhD, the candidate will join a rich interdisciplinary research environment spanning advanced AI, multimodal learning, perception, and intelligent sensing. The position offers close collaboration with leading experts from both institutions and access to a unique combination of scientific excellence and real-world impact.

Required background : A Master’s degree in AI, Computer Science, Electrical Engineering, Robotics, Applied Mathematics, or a related field, with preferable knowledge in machine learning, deep learning and embedded AI.

Type of work : 70% modeling/simulation, 20% experimental, 10% literature

Supervisor : Lynn Houthuys (VUB)

Co-supervisor : Tom De Schepper

Daily advisor : Diana Gomes, Julie Moeyersoms The reference code for this position is 2027-091 . Mention this reference code in your application

L'offre d'emploi a été publiée il y a 2 jours
Des emplois similaires qui pourraient vous intéresserBasé sur l'offre Learning to Perceive in Degraded Environments à Louvain
  •  ...reliability issues, ultimately resulting in a PIC failure. The degradation of device performance over time is linked to defects, either pre...  .... Feel free to reach out to this email if you would like to learn more about this PhD opportunity: ****@*****.***... 
    Suggéré

    imec

    Louvain
    il y a 2 jours
  •  ...optimization and higher electric fields in the junction, but these same conditions can accelerate defect generation and reliability degradation. In fact, phenomena usually associated with transistor reliability, such as bias temperature instability [2], charge trapping [3]... 
    Suggéré

    imec

    Louvain
    il y a 2 jours
  •  ...MEMS fabrication into actionable knowledge. Existing machine learning approaches have shown promise but often struggle with limited...  ...tools such as Python, MATLAB, or similar scientific computing environments. An interest in machine learning, artificial intelligence,... 
    Suggéré

    imec

    Louvain
    il y a 2 jours
  •  ...particular, imperfect motion compensation can introduce phase errors, artefacts, and image defocusing. Recent developments in deep learning and deep unfolding offer promising ways to combine radar-domain knowledge with trainable components for improved image... 
    Suggéré
    Stage

    imec

    Louvain
    il y a 2 jours
  •  ...chiplet systems, package warpage and thermo-mechanical stresses can degrade thermal interfaces, leading to increased junction temperatures...  ..., experimental characterization, and Physics-Informed Machine Learning (PIML) to accelerate the design of future chiplet packages. By... 
    Suggéré

    imec

    Louvain
    il y a 2 jours
  •  ...innovation, and impact.  We are now looking for a Machine Learning (ML) Engineer to join the Machine Learning Expertise Unit at...  ...international, interdisciplinary, collaborative, and supportive work environment, which emphasizes diversity and inclusion. An environment... 

    VIB

    Louvain
    Il y a 2 mois
  •  ...ML+HPC hybrid workloads that combine numerical simulation, machine learning, data analytics, and AI-driven scientific discovery. This...  ...existing systems. Machine-learning approaches offer an opportunity to learn complex relationships directly from application executions and... 

    imec

    Louvain
    il y a 2 jours
  •  ...measured outcomes relate to each other. Recent advances in machine learning offer a way to change this. Transformer-based foundation models...  ...-JEPA), latent world models and continual learning methods can learn from large amounts of unlabelled data, predict outcomes under... 
    Stage
    Recrutement immédiat

    imec

    Louvain
    il y a 2 jours
  •  ...infeasible, motivating the need for new computer vision and machine learning techniques. This Master’s internship project addresses...  ...strict constraints is critical. The selected intern/student will learn conventional process flow and will be responsible to work... 
    Stage
    Recrutement immédiat

    imec

    Louvain
    il y a 2 jours
  •  ...failure analysis. This project will investigate novel machine learning frameworks capable of achieving high detection accuracy despite...  ...MATLAB) and machine learning frameworks (e.g., PyTorch, scikit-learn). Knowledge of signal processing, computer vision, or acoustic... 
    Stage
    Travail posté

    imec

    Louvain
    il y a 7 jours
  •  ...data interpretation, identify possible degradation or failure mechanisms, and propose follow...  ...Present device physics and reliability learnings in technical reviews, project meetings,...  ..., multicultural, and informal working environment with ample possibilities to take... 
    Temps complet

    imec

    Louvain
    il y a 7 jours
  •  ...and overlay errors—misalignments that may degrade electrical performance or cause device...  ...axisymmetric physics-based mechanical modeling environment (coupled fluidic-structrual) to study...  ...-wafer bonding simulations Apply the learnings from physics based models to advance... 

    imec

    Louvain
    il y a 2 jours
  •  ...misalignments, phase errors, or signal degradation. To counteract these effects, feedback control...  ....   Good k nowledge of Cadence environment for schematic entry, simulations and...  ...-solving skills .   Eagerness to learn and innovate .   Good communication... 
    Stage

    imec

    Louvain
    il y a 2 jours
  •  ...embedded systems development project within a high-tech industrial environment. The program involves communication between embedded devices...  ...Detect situations that may lead to instability or degraded system behavior Investigating interactions between: CAN tools... 
    Temps complet
    Emploi en CDI

    Médiane Benelux

    Louvain
    il y a 12 jours
  •  ...transistors [3,4]. We know that these devices degrade. But why? The goal of this PhD is to...  ...partners within the imec research environment. This PhD is an opportunity to work on...  ...by open scientific questions, wants to learn across disciplines, and is motivated to... 

    imec

    Louvain
    il y a 2 jours
  •  ...work with customer technical teams to resolve concerns, reduce perceived mission risk and support internal approvals. Represent...  ...your fingertips A competitive salary A friendly working environment. Ready to make an impact? ~ Apply now by submitting your CV... 
    Emploi contractuel
    Temps complet
    À distance

    Simera Sense

    Louvain
    il y a 16 jours
  •  ...of the most advanced high-k dielectrics. Understanding the degradation of these materials is key to guarantee the reliability of the...  ...the diffusion of oxygen vacancies in Al-doped HfO 2 . These learnings will strengthen the current understanding of high-k dielectrics... 
    Stage

    imec

    Louvain
    il y a 2 jours
  •  ...dielectrics. Particular emphasis will be placed on identifying the critical bond configurations that initiate degradation and determining how local atomic environments influence breakdown susceptibility. By extracting material-specific bond strength descriptors and... 
    Stage

    imec

    Louvain
    il y a 2 jours
  •  ...hands-on engineering to leading multiple teams in a fast-growth environment. You excel at unifying engineers toward an ambitious, shared...  ...to share their opinions, actively collaborate, and continue to learn and grow.   Do you want to make a difference? What are you... 
    Temps complet

    Guardsquare

    Louvain
    il y a 1 jour
  •  ...from the complex interaction between device aging, interconnect degradation, and workload-dependent operating conditions. Current...  ...project will combine physics-based reliability modeling, machine learning, and silicon validation through dedicated reliability test vehicles... 
    Travail posté

    imec

    Louvain
    il y a 2 jours
  •  ...classic computer vision to modern machine learning, we can solve challenging real-world...  ...understanding. If you thrive in a team environment, enjoy learning every day, and want your...  ...value your passion for technology, drive to learn, and motivation to make a difference.... 

    KLA

    Louvain
    il y a 7 jours
  •  ...Software Engineers working within an agile software development environment. The ideal candidate started their career technically and has a...  ...to share their opinions, actively collaborate, and continue to learn and grow.   Do you want to make a difference? What are you... 
    Temps complet

    Guardsquare

    Louvain
    il y a 1 jour
  • 49600 € - 68200 € par année

     ...benefit from a supportive work culture that encourages you to learn, develop, and grow your career as you take on challenges and drive...  ...colors and working with electricity, the ability to work in an environment with noise that may be difficult for some individuals with... 
    Temps complet
    Travail à domicile

    Applied Materials

    Louvain
    il y a 2 jours
  •  ...cultivating a connected culture where everyone has the opportunity to learn, grow and succeed together. Job Overview Why join us to...  ...to learn and develop technical capability within a consultancy environment. Have the ability to travel to the UK for site visits... 

    Jensen Hughes

    Louvain
    il y a 1 jour
  •  ...employer and proud of our open, multicultural, and informal working environment with ample possibilities to take initiative and show...  ...wafer probers and/or lab instruments. Easily shares knowledge and learns from others. Has proven experience in writing technical documentation... 

    imec

    Louvain
    il y a 7 jours
  •  ...employer and proud of our open, multicultural, and informal working environment with ample possibilities to take initiative and show...  ...immersion/EUV) is a plus. You are well organized and eager to learn. You have good technical problem-solving skills and are comfortable... 

    imec

    Louvain
    il y a 7 jours
  •  ...complex challenges. From electron and photon optics to machine learning and data analytics, we seek perfection at the most fundamental...  ...design our programs to reflect our commitment to an inclusive environment, while ensuring we provide benefits that meet the diverse... 

    KLA

    Louvain
    il y a 7 jours
  •  ...reliable operation of advanced semiconductor equipment within our R&D environment in Leuven, Belgium. You will work hands-on with new and first-...  ...that shape how we live, work, and connect. To learn more about ASM, find us at asm.com and on LinkedIn, Facebook, Instagram... 

    ASM

    Louvain
    il y a 7 jours
  •  ...readiness of SEM tools within a 24/7 production environment Collaborate with First Line Support (FLS...  ...training, onboarding, and continuous learning within the team Contribute to knowledge...  ...similar industrial experience Eager to learn and self-organized Good sense of urgency... 

    imec

    Louvain
    il y a 7 jours
  •  ...processing and related Process and Measurement techniques. You will learn in detail how the imec Fabs operate. Then you will start your...  ...and proud of our open, multicultural, and informal working environment with ample possibilities to take initiative and show responsibility... 

    imec

    Louvain
    il y a 7 jours

Voulez-vous recevoir plus d'offres d'emploi ?

S'abonner et recevoir des offres d'emploi similaires à Learning to Perceive in Degraded Environments. Soyez parmi les premiers à postuler !