Related papers: Model Validity in Observers: When to Increase the …
Model visualizations provide information that outputs alone might miss. But can we trust that model visualizations reflect model behavior? For instance, can they diagnose abnormal behavior such as planted backdoors or overregularization? To…
Accurate simulation and validation of advanced driver assistance systems requires accurate sensor models. Modeling automotive radar is complicated by effects such as multipath reflections, interference, reflective surfaces, discrete cells,…
It has been for a long time to use big data of autonomous vehicles for perception, prediction, planning, and control of driving. Naturally, it is increasingly questioned why not using this big data for risk management and actuarial…
Formal verification provides strong safety guarantees but only for models of cyber-physical systems. Hybrid system models describe the required interplay of computation and physical dynamics, which is crucial to guarantee what computations…
Autonomous vehicles are increasingly introduced into our lives. Yet, people's misunderstanding and mistrust have become the major obstacles to the use of these technologies. In response to this problem, proper work must be done to increase…
We present a randomized controlled trial for a model-in-the-loop regression task, with the goal of measuring the extent to which (1) good explanations of model predictions increase human accuracy, and (2) faulty explanations decrease human…
How effective are recent advancements in autonomous vehicle perception systems when applied to real-world autonomous vehicle control? While numerous vision-based autonomous vehicle systems have been trained and evaluated in simulated…
The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration…
The Responsibility-Sensitive Safety (RSS) model offers provable safety for vehicle behaviors such as minimum safe following distance. However, handling worst-case variability and uncertainty may significantly lower vehicle permissiveness,…
Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for precisely controlling large language models. While steering efficacy has been widely studied,…
Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to…
Developing safety and efficiency applications for Connected and Automated Vehicles (CAVs) require a great deal of testing and evaluation. The need for the operation of these systems in critical and dangerous situations makes the burden of…
Learning-based controllers are often purposefully kept out of real-world applications due to concerns about their safety and reliability. We explore how state-of-the-art world models in Model-Based Reinforcement Learning can be utilized…
ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g.,…
Driver distractions are known to be the dominant cause of road accidents. While monitoring systems can detect non-driving-related activities and facilitate reducing the risks, they must be accurate and efficient to be applicable.…
Despite extensive research, the testing of autonomous driving systems (ADS) landscape remains fragmented, and there is currently no basis for an informed technical assessment of the importance and contribution of the current state of the…
Autonomous driving has been the subject of increased interest in recent years both in industry and in academia. Serious efforts are being pursued to address legal, technical and logistical problems and make autonomous cars a viable option…
The capability to follow a lead-vehicle and avoid rear-end collisions is one of the most important functionalities for human drivers and various Advanced Driver Assist Systems (ADAS). Existing safety performance justification of the…
A classical method for model-checking timed properties-such as those expressed using timed extensions of temporal logic-is to rely on the use of observers. In this context, a major problem is to prove the correctness of observers.…
Visual validation of regression models in scatterplots is a common practice for assessing model quality, yet its efficacy remains unquantified. We conducted two empirical experiments to investigate individuals' ability to visually validate…