Constructor Education and Research Genossenschaft

Systems and methods include detecting obstacles and drivable areas by an autonomous vehicle by inputting image and map data into a neural network to extract feature vectors. A transformer encoder converts these vectors from camera space to Bird's Eye View (BEV) space. A detection head identifies objects, and a segmentation head generates a BEV map showing objects and drivable surfaces. Attributes from both heads are compared, and the segmentation head's weights are updated accordingly, resulting in an updated BEV segmentation map output by the updated segmentation head.

Disclosed herein are systems and method for an artificial intelligence (AI)-based monitoring of a formation of racers. In one aspect, a method includes: obtaining geolocation data for a group of racers on a race course and a digital map of the race course configured to track movement of the group of racers in a formation; determining a type of race and a type of race course, and at least one assigned formation for the group of racers corresponding to the type of race and the race course along a plurality of locations; analyzing the digital map of the race course and the geolocation data of racers at the plurality of locations using a trained formation neural network trained to analyze group formations for different types of races and different types of race courses; and displaying a formation statistics for the at least one racer based on the analysis.

Systems and methods for creating a training script on a virtual laboratory instance running in an e-learning infrastructure. The method comprises deploying a virtual laboratory instance from a template on e-learning infrastructure. The virtual laboratory instance includes preconfigured training software and an action interception tool. The method further comprises intercepting system events at the action interception tool corresponding to training software operation, pre-processing intercepted events by filtering and grouping events into an action-centric dataset, generating a training script using a machine learning model, based on an action-centric dataset, in a human-readable format, and storing the training script in a structured text-based format file.

A speech engine inputs, into an encoder-decoder machine learning (ML) model, an input text and an audio clip including a voice reciting a speech, wherein the encoder-decoder ML model is trained to generate acoustic features representing an emulation of the voice reciting the input text. The encoder-decoder ML model is configured to: receive a phoneme sequence of the input text; predict a duration of each phoneme in the phoneme sequence; predict a pitch and an energy for reciting the input text based on the partially masked acoustic representations obtained from the audio clip; and generate acoustic features based on (1) the duration of phoneme in the phoneme sequence, (2) the predicted pitch, and (3) the predicted energy The speech engine inputs the generated acoustic features into a vocoder model configured to generate an output waveform representing the input text being recited by the emulation of the voice.

A system inputs a first audio sample into a co-speech engine that is configured to generate a first output data file comprising motion data of a virtual avatar over a period of time, wherein the motion data represents one or more gestures identified by the co-speech engine as corresponding to the first audio sample. The system extracts a first plurality of features from the first output data file. The system extracts a second plurality of features from a second output data file. The system determines a difference value by comparing the first plurality of features with the second plurality of features. The system updates weights associated with the co-speech engine based on the difference value between the first plurality of features and the second plurality of features. The system executes the co-speech engine with the updated weights on a third audio sample to generate a third output data file.

Disclosed herein are systems and methods for training a text-to-speech machine learning model. A method includes: inputting training text into an acoustic model configured to generate an intermediate representation including predicted latent features for a vocoder model that further generates a waveform of speech reciting the training text; inputting a target waveform into a self-supervising learning (SSL) model configured to generate a vector representation of the target waveform, wherein the target waveform is true speech reciting the training text; extracting and summing SSL features from a plurality of layers of the SSL model; computing a loss between a sum of the SSL features from the SSL model and the predicted latent features from the acoustic model; updating, using backpropagation, weights of the acoustic model based on the loss; and executing the acoustic model with the updated weights on a test text to generate the intermediate representation.

Disclosed herein are systems and method for monitoring race car pit crews and generating optimization recommendations. In one aspect, a method includes: receiving, from at least one camera, a video clip of a crew member performing service of a race car; detecting, using a machine learning algorithm, an error made by the crew member while performing the service; in response to determining that the error has been performed by the crew member more than a threshold number of times within a period of time, identifying a sequence of events leading up to the error; generating, using the machine learning algorithm, a recommended change in the sequence to prevent the error from reoccurring in a future service; and transmitting an instruction including the recommended change to a communicative device of the crew member.

Disclosed herein are systems and method for a machine learning (ML)-based analysis of multiple simultaneous events in a video. In one aspect, a method includes: obtaining a video of objects that potentially involved in an activity; identifying the objects in the video by analyzing the video using a trained object detection ML model; cropping the video into a plurality of video clips; obtaining a list of roles for the activity and a list of actions associated the role; determining a role for each object involved in the activity by analyzing actions and/or interactions with the objects for each object by executing a trained role recognition ML model in each video clip; and evaluating a performance for each object in their role while performing the activity using a trained performance evaluation ML model.

Disclosed herein are systems and methods for a machine-learning based method for assessing academic performance of a learner and providing learning recommendations. The method includes obtaining assessment materials for a learner. The method also includes analyzing answers using a trained test assessment LLM. The method includes analyzing the test feedback using a trained course assessment LLM configured to evaluate a proficiency with the course materials and to generate a course feedback comprising expected answers and indicating a level of proficiency with the course materials. The method includes analyzing the course feedback to evaluate a proficiency with topics of study based on the course feedback for given topics and the past academic performance data of the learner, and to generate a topic feedback. The method further includes generating a plurality of personalized learning recommendations for topics of study in which the learner has a level of proficiency below a proficiency threshold.

Disclosed herein are systems and methods for improving responses from LLMs by modifying chat history of at least one LLM. In one aspect, an exemplary method includes: obtaining a query; transmitting a prompt based on the query for input into a first LLM; obtaining a first response from the first LLM; displaying the query along with the first response from the first LLM; modifying a chat history of the first LLM based on obtaining a selection of at least one portion of the first response from the first LLM; combining the selected portions of the first response, the prompt, and the modified chat history into a new prompt for input into the second LLM; transmitting the new prompt for input into the second LLM; and obtaining and displaying a new response from the second LLM based on the new prompt.