25 km

Continental AG

1

Passende Jobs zu Ihrer Suche ...

... immer aktuell und kostenlos per E-Mail.
Sie können den Suchauftrag jederzeit abbestellen.
Es gilt unsere Datenschutzerklärung. Sie erhalten passende Angebote per E-Mail. Sie können sich jederzeit wieder kostenlos abmelden.

Informationen zur Anzeige:

PhD Student AI - Failure Case Suppression for Perception (m/f/diverse)
Berlin
Aktualität: 10.08.2022

Anzeigeninhalt:

10.08.2022, Continental AG
Berlin
PhD Student AI - Failure Case Suppression for Perception (m/f/diverse)
We are searching for a research scientist (m/f/diverse) to join our artificial intelligence (AI) team in Berlin. As part of the central pre-development department, our goal is to develop and enable the use of AI in future Continental products. You will work in an innovative team of specialists and students with the goal of a Ph.D. The traceability of an AI function's decision is essential, especially for safety-critical systems such as autonomous driving. In this context, two aspects will be considered in this thesis. First, the development of methods for plausible AI perception function predictions by estimating uncertainties in decisions through additional input of knowledge. And second, the investigation of methods for self-explanation of predictions by extracted knowledge from the AI function with the goal to realize an assisted error correction. The goal is to develop a prototype system, which allows an interpretation of the reliability by means of metrics, as well as showing strategies for failure correction. Example: Consider a system with a perception function and a subsequent path planning component. The perception function is a deep neural network (DNN) that determines a semantic segmentation of images. The plausibility check of the prediction is intended to determine the uncertainty in the decision, such that this can be considered during path planning. However, since the confidence statements of DNNs are unreliable, further methods must be applied. Apart from calibration methods also knowledge, e.g., physical correlations, shall be used to gain plausible predictions. For the self-explanation of DNN predictions, the latent features are used. For this purpose, knowledge is extracted from a DNN in the first step and finally used in the self-explanation component to increase the comprehensibility of the decision. For example, in the case of pedestrian detection, the first step could be to determine concepts (e.g., hands, torso, or head) that play a role in the decision process explaining the predictions. This case becomes interesting if a person is occluded and only certain concepts are visible. Finally, detected failure cases can be analyzed using the self-explanation and appropriate strategies shall be developed to correct them. Goals of thesis: Development of approaches for the plausibility check of AI perception functions decisions, by means of estimation of uncertainties using additional world knowledge and extracted concepts Development of a self-explanation component for explaining DNN decisions Creation of strategies to resolve failure cases using the self-explanation component Integrating the plausibility check and self-explanation component into a simulation to run experiments and demonstrations Development of KPIs to monitor the effectiveness of the developed methods Working in the AI Campus in Berlin means being part of a highly motivated and growing team of researchers working in the field of artificial intelligence. Being located in one of the German centers for AI, we strive to work on the frontier of research by having open exchange with experts and highly influential players in the community. Frequent talks, gatherings, and discussions as well as formal and informal team events ensure prompt spread of information. In our freshly established team of mostly Ph.D. students, we are maintaining an harmonious atmosphere of easy-going collaboration and exchange. Despite this inviting culture of togetherness, we will provide you with enough flexibility in terms of working time and location. Doing a Ph.D. in Continental is going to equip you with exceptional qualification, network, and industrial experience in the future field of autonomous driving.
Studied artificial intelligence, computer science, mathematics, physics, robotics or related fields Intensively worked with artificial-intelligence-related algorithms Desirable to know about autonomous systems or to be interested in Able to professionally speak and write in English language Speaking or eager to learn German Curious about giving new technologies a practical try Independent, creative, and proactive working style Actively working and communicating in a team

Berufsfeld

Standorte