This paper presents a novel monitoring framework that infers the level of collision risk for autonomous vehicles (AV s) based on their object detection performance. The framework takes two sets of predictions from different algorithms and associates their inconsistencies with the collision risk via fuzzy inference. The first set of predictions is obtained by retrieving safety-critical 2.5D objects from a depth map, and the second set comes from the ordinary AV's 3D object detector. We experimentally validate that, based on Intersection-over-Union (IoU) and a depth discrepancy measure, the inconsis-tencies between the two sets of predictions strongly correlate to the error of the 3D object detector against ground truths. This correlation allows us to construct a fuzzy inference system and map the inconsistency measures to an AV collision risk indicator. In particular, we optimize the fuzzy inference system towards an existing offline metric that matches AV collision rates well. Lastly, we validate our monitor's capability to produce relevant risk estimates with the large-scale nuScenes dataset and demonstrate that it can safeguard an AV in closed-loop simulations.

This paper presents Ego-Centric Intersection-over-Union (EC-IoU), addressing the limitation of the standard IoU measure in characterizing safety-related performance for object detectors in navigating contexts. Concretely, we propose a weighting mechanism to refine IoU, allowing it to assign a higher score to a prediction that covers closer points of a ground-truth object from the ego agent’s perspective. The proposed EC-IoU measure can be used in typical evaluation processes to select object detectors with better safety-related performance for downstream tasks. It can also be integrated into common loss functions for model fine-tuning. While geared towards safety, our experiment with the KITTI dataset demonstrates the performance of a model trained on EC-IoU can be better than that of a variant trained on IoU in terms of mean Average Precision as well.

We introduce a distributed control method for coordinating multiple vehicles in the framework of an automated valet parking (AVP) system. The control functionality is distributed between an infrastructure server, called parking area management (PAM) system, and local autonomous vehicle control units. Via a vehicle-to-infrastructure (V2I) communication interface, model predictive control (MPC) decisions of the vehicles are shared with the coordination unit in the PAM. This unit in turn computes a coupling feedback which is shared with the vehicles. The control system is integrated in an automated test-system to cope with the high test requirements and short development cycles of highly automated systems. Evaluations conducted with the test-system show the functionality of the proposed distributed control method for multi-vehicle coordination. Results indicate safe coordination, and an efficiency increase compared to an uncoordinated method in an AVP simulation environment.

In this work, we present novel VR training strategies that incorporate a hybrid trainer model to train force. For modeling the trainer skill, weighted K-means algorithm in parameter space with LS optimization is implemented. The efficiency of the training strategies is verified via user tests in frame of a bone drilling training application. An objective evaluation method based on n dimensional Euclidean distances is introduced to assess user tests results. It is shown that the proposed strategies improve the student skill and accelerate force learning.

In this paper a multi-user virtual training system concept for force skill training is presented. A trainer and a student connect to a common virtual environment via their individual haptic displays. The student realizes the virtual task, while the trainer observes him/her visually, acoustically and/or haptically. The trainer has a chance to correct the student verbally or haptically. Alternatively, the observation duty is given to the student, while the trainer demonstrates a task. Depending on the combinations of these observation/correction possibilities, three novel training strategies have been developed. Force information is exchanged on a separate communication line, which minimizes the time delay. The efficiency of the developed training strategies is verified via user tests on the bone drilling medical training system that was developed in our laboratories previously. Last, but not least, a special attention is paid to objective assessment of the user tests' results. Thus, a method based on distances in n dimensional Euclidean space is developed and implemented.

In this work a virtual reality medical training system (MTS) for bone drilling skill training is presented. For this purpose a novel controller algorithm, two graphical user interfaces for teaching and simulating purposes are developed. A 3 DOF haptic display that is developed in our laboratory is used for force feedback. Several user tests are performed to validate how the developed MTS helps for skill improvement. The effects of adding acoustic feedback and the advantages of using a 3 DOF haptic display instead of 1 DOF are investigated. Preliminary user studies suggest that the proposed system can be a powerful tool for teaching how to drill into bone.