Learning complex navigation behaviors in simulation and successfully transferring them to the real world remains a significant challenge due to the sim-to-real gap. To address this issue, we propose a hybrid reconstruction approach that combines Light Detection and Ranging (LiDAR) data and monocular images to create visually and structurally realistic simulated environments. Specifically, we extract an accurate mesh from LiDAR measurements and integrate it with geometry-consistent Three-Dimensional Gaussian Splatting (3DGS) to render photorealistic images. Additionally, we present an end-to-end neural network designed to generate control commands for a mobile robot, and it is used to assess the effectiveness of the hybrid reconstructions in narrowing the sim-to-real gap. In the proposed model, we introduce a novel auxiliary branch and define loss functions to improve the network’s ability to learn safe and robust actions. The method, which is based on imitation learning, is evaluated by deploying it on a real robot to navigate over a total distance of 3.5 kilometers, and experimental results show that models trained purely in simulation achieve performance comparable to those trained on real-world data.

Differential testing is a highly effective technique for automatically detecting software bugs and vulnerabilities when the specifications involve an analysis over multiple executions simultaneously. Differential fuzzing, in particular, operates as a guided randomized search, aiming to find (similar) inputs that lead to a maximum difference in software outputs or their behaviors. However, fuzzing, as a dynamic analysis, lacks any guarantees on the absence of bugs: from a differential fuzzing campaign that has observed no bugs (or a minimal difference), what is the risk of observing a bug (or a larger difference) if we run the fuzzer for one or more steps?This paper investigates the application of Extreme Value Theory (EVT) to address the risk of missing or underestimating bugs in differential fuzzing. The key observation is that differential fuzzing as a random process resembles the maximum distribution of observed differences. Hence, EVT, a branch of statistics dealing with extreme values, is an ideal framework to analyze the tail of the differential fuzzing campaign to contain the risk. We perform experiments on a set of real-world Java libraries and use differential fuzzing to find information leaks via side channels in these libraries. We first explore the feasibility of EVT for this task and the optimal hyperparameters for EVT distributions. We then compare EVT-based extrapolation against baseline statistical methods like Markov’s as well as Chebyshev’s inequalities, and the Bayes factor. EVT-based extrapolations outperform the baseline techniques in 14.3% of cases and tie with the baseline in 64.2% of cases. Finally, we evaluate the accuracy and performance gains of EVT-enabled differential fuzzing in real-world Java libraries, where we reported an average saving of tens of millions of bytecode executions by an early stop.

The tracking problem remains difficult because trackers may lose the target due to occlusions or changes in the target's appearance and start tracking another one, making it difficult to detect when they fail. To deal with these problems, we design a novel method to track objects robustly by fusing different trackers, using an Extended Kalman Filter, which helps to detect these situations and correct them. We use our tracker-fusion in a mobile robot to follow a pedestrian while also avoiding dynamic obstacles, an aspect not usually analyzed in pedestrian following. The perception of the environment is done with a 3D LiDAR and the tracking is performed on front-view images constructed from the point cloud. We show that by fusing two different trackers, the robot can follow the target during long experimental sessions where there are occlusions of the target by other people. The method is more precise and robust than using the trackers without the fusion.

Single Object Tracking methods are yet not robust enough because they may lose the target due to occlusions or changes in the target’s appearance, and it is difficult to detect automatically when they fail. To deal with these problems, we design a novel method to improve object tracking by fusing complementary types of trackers, taking advantage of each other’s strengths, with an Extended Kalman Filter to combine them in a probabilistic way. The environment perception is performed with a 3D LiDAR sensor, so we can track the object in the point cloud and also in the front-view image constructed from the point cloud. We use our tracker-fusion method in a mobile robot to follow pedestrians, also considering the dynamic obstacles in the environment to avoid them. We show that our method allows the robot to follow the target accurately during long experimental sessions where the trackers independently fail, demonstrating the robustness of our tracker-fusion strategy.