7 papers
Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models
Franz Motzkus, Sebastian Bernhard
The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavio…
CN-CBF: Composite Neural Control Barrier Function for Robot Navigation in Dynamic Environments
Bojan DerajiÄ, Sebastian Bernhard, Wolfgang Hönig
Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One prevalent approach is safety filtering b…
ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworks
Bojan DerajiÄ, Sebastian Bernhard, Wolfgang Hönig
Control barrier functions (CBFs) have been demonstrated as an effective method for safety-critical control of autonomous systems. Although CBFs are simple to deploy, their design r…
Residual Neural Terminal Constraint for MPC-based Collision Avoidance in Dynamic Environments
Bojan DerajiÄ, Mohamed-Khalil Bouzidi, Sebastian Bernhard +1
In this paper, we propose a hybrid MPC local planner that uses a learning-based approximation of a time-varying safe set, derived from local observations and applied as the MPC ter…
Model Predictive Control for Crowd Navigation via Learning-Based Trajectory Prediction
Mohamed Parvez Aslam, Bojan Derajic, Mohamed-Khalil Bouzidi +2
Safe navigation in pedestrian-rich environments remains a key challenge for autonomous robots. This work evaluates the integration of a deep learning-based Social-Implicit (SI) ped…
Learning Maximal Safe Sets Using Hypernetworks for MPC-based Local Trajectory Planning in Unknown Environments
Bojan DerajiÄ, Mohamed-Khalil Bouzidi, Sebastian Bernhard +1
This paper presents a novel learning-based approach for online estimation of maximal safe sets for local trajectory planning in unknown static environments. The neural representati…