Christian Pek
YOU?
Author Swipe
View article: Belief Control Barrier Functions for Risk-Aware Control
Belief Control Barrier Functions for Risk-Aware Control Open
Ensuring safety in real-world robotic systems is often challenging due to unmodeled disturbances and noisy sensors. To account for such stochastic uncertainties, many robotic systems leverage probabilistic state estimators such as Kalman f…
View article: SpaTiaL: monitoring and planning of robotic tasks using spatio-temporal logic specifications
SpaTiaL: monitoring and planning of robotic tasks using spatio-temporal logic specifications Open
Many tasks require robots to manipulate objects while satisfying a complex interplay of spatial and temporal constraints. For instance, a table setting robot first needs to place a mug and then fill it with coffee, while satisfying spatial…
View article: Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks
Generating Scenarios from High-Level Specifications for Object Rearrangement Tasks Open
Rearranging objects is an essential skill for robots. To quickly teach robots new rearrangements tasks, we would like to generate training scenarios from high-level specifications that define the relative placement of objects for the task …
View article: Belief Control Barrier Functions for Risk-aware Control
Belief Control Barrier Functions for Risk-aware Control Open
Ensuring safety in real-world robotic systems is often challenging due to unmodeled disturbances and noisy sensor measurements. To account for such stochastic uncertainties, many robotic systems leverage probabilistic state estimators such…
View article: Aligning Human Preferences with Baseline Objectives in Reinforcement Learning
Aligning Human Preferences with Baseline Objectives in Reinforcement Learning Open
Practical implementations of deep reinforcement learning (deep RL) have been challenging due to an amplitude of factors, such as designing reward functions that cover every possible interaction. To address the heavy burden of robot reward …
View article: Risk-aware Spatio-temporal Logic Planning in Gaussian Belief Spaces
Risk-aware Spatio-temporal Logic Planning in Gaussian Belief Spaces Open
In many real-world robotic scenarios, we cannot assume exact knowledge about a robot’s state due to unmodeled dynamics or noisy sensors. Planning in belief space addresses this problem by tightly coupling perception and planning modules to…
View article: Increasing Perceived Safety in Motion Planning for Human-Drone Interaction
Increasing Perceived Safety in Motion Planning for Human-Drone Interaction Open
Safety is crucial for autonomous drones to operate close to humans. Besides avoiding unwanted or harmful contact, people should also perceive the drone as safe. Existing safe motion planning approaches for autonomous robots, such as drones…
View article: SpaTiaL: Monitoring and Planning of Robotic Tasks Using Spatio-Temporal Logic Specifications
SpaTiaL: Monitoring and Planning of Robotic Tasks Using Spatio-Temporal Logic Specifications Open
Many tasks require robots to manipulate objects while satisfying a complex interplay of spatial and temporal constraints. For instance, a table setting robot first needs to place a mug and then fill it with coffee, while satisfying spatial…
View article: Correct-by-Construction Runtime Enforcement in AI -- A Survey
Correct-by-Construction Runtime Enforcement in AI -- A Survey Open
Runtime enforcement refers to the theories, techniques, and tools for enforcing correct behavior with respect to a formal specification of systems at runtime. In this paper, we are interested in techniques for constructing runtime enforcer…
View article: Foresee the Unseen: Sequential Reasoning about Hidden Obstacles for Safe Driving
Foresee the Unseen: Sequential Reasoning about Hidden Obstacles for Safe Driving Open
Safe driving requires autonomous vehicles to anticipate potential hidden traffic participants and other unseen objects, such as a cyclist hidden behind a large vehicle, or an object on the road hidden behind a building. Existing methods ar…
View article: Evaluating Sequential Reasoning about Hidden Objects in Traffic
Evaluating Sequential Reasoning about Hidden Objects in Traffic Open
Hidden traffic participants pose a great challenge for autonomous vehicles. Previous methods typically do not use previous observations, leading to over-conservative behavior. In this paper, we present a continuation of our work on reasoni…
View article: Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies
Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies Open
Reinforcement learning has shown great potential for learning sequential decision-making tasks. Yet, it is difficult to anticipate all possible real-world scenarios during training, causing robots to inevitably fail in the long run. Many o…
View article: Human-Feedback Shield Synthesis for Perceived Safety in Deep Reinforcement Learning
Human-Feedback Shield Synthesis for Perceived Safety in Deep Reinforcement Learning Open
Despite the successes of deep reinforcement learning (RL), it is still challenging to obtain safe policies. Formal verifi- cation approaches ensure safety at all times, but usually overly restrict the agent’s behaviors, since they assume a…
View article: Learning Task Constraints in Visual-Action Planning from Demonstrations
Learning Task Constraints in Visual-Action Planning from Demonstrations Open
Visual planning approaches have shown great success for decision making tasks with no explicit model of the state space. Learning a suitable representation and constructing a latent space where planning can be performed allows non-experts …
View article: Risk-aware Motion Planning for Autonomous Vehicles with Safety Specifications
Risk-aware Motion Planning for Autonomous Vehicles with Safety Specifications Open
Ensuring the safety of autonomous vehicles (AVs) in uncertain traffic scenarios is a major challenge. In this paper, we address the problem of computing the risk that AVs violate a given safety specification in uncertain traffic scenarios,…
View article: Encoding Human Driving Styles in Motion Planning for Autonomous Vehicles
Encoding Human Driving Styles in Motion Planning for Autonomous Vehicles Open
Driving styles play a major role in the acceptance and use of autonomous vehicles. Yet, existing motion planning techniques can often only incorporate simple driving styles that are modeled by the developers of the planner and not tailored…
View article: Fail-Safe Motion Planning for Online Verification of Autonomous Vehicles Using Convex Optimization
Fail-Safe Motion Planning for Online Verification of Autonomous Vehicles Using Convex Optimization Open
Safe motion planning for autonomous vehicles is a challenging task, since the exact future motion of other traffic participant is usually unknown. In this article, we present a verification technique ensuring that autonomous vehicles do no…
View article: CommonRoad Drivability Checker: Simplifying the Development and Validation of Motion Planning Algorithms
CommonRoad Drivability Checker: Simplifying the Development and Validation of Motion Planning Algorithms Open
Collision avoidance, kinematic feasibility, and road-compliance must be validated to ensure the drivability of planned motions for autonomous vehicles. Although these tasks are highly repetitive, computationally efficient toolboxes are sti…
View article: Provably-Safe Cooperative Driving via Invariably Safe Sets
Provably-Safe Cooperative Driving via Invariably Safe Sets Open
We address the problem of provably-safe cooperative driving for a group of vehicles that operate in mixed traffic scenarios, where both autonomous and human-driven vehicles are present. Our method is based on Invariably Safe Sets (ISSs), w…
View article: Using Reachable Sets for Trajectory Planning of Automated Vehicles
Using Reachable Sets for Trajectory Planning of Automated Vehicles Open
The computational effort of trajectory planning for automated vehicles often increases with the complexity of the traffic situation. This is particularly problematic in safety-critical situations, in which the vehicle must react in a timel…
View article: Provably-Correct and Comfortable Adaptive Cruise Control
Provably-Correct and Comfortable Adaptive Cruise Control Open
Adaptive cruise control is one of the most common comfort features of road vehicles. Despite its large market penetration, current systems are not safe in all driving conditions and require supervision by human drivers. While several previ…
View article: Provably Safe Motion Planning for Autonomous Vehicles Through Online Verification
Provably Safe Motion Planning for Autonomous Vehicles Through Online Verification Open
This thesis introduces fail-safe motion planning as the first approach to guarantee legal safety of autonomous vehicles in arbitrary traffic situations. The proposed safety layer verifies whether intended trajectories comply with legal saf…
View article: Computationally Efficient Safety Falsification of Adaptive Cruise Control Systems
Computationally Efficient Safety Falsification of Adaptive Cruise Control Systems Open
Falsification aims to disprove the safety of systems by providing counter-examples that lead to a violation of safety properties. In this work, we present two novel falsification methods to reveal safety flaws in adaptive cruise control (A…
View article: Set-Based Prediction of Pedestrians in Urban Environments Considering Formalized Traffic Rules
Set-Based Prediction of Pedestrians in Urban Environments Considering Formalized Traffic Rules Open
Set-based predictions can ensure the safety of planned motions, since they provide a bounded region which includes all possible future states of nondeterministic models of other traffic participants. However, while autonomous vehicles are …
View article: High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning
High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning Open
Machine learning techniques have been shown to outperform many rule-based systems for the decision-making of autonomous vehicles. However, applying machine learning is challenging due to the possibility of executing unsafe actions and slow…
View article: Computationally Efficient Fail-safe Trajectory Planning for Self-driving Vehicles Using Convex Optimization
Computationally Efficient Fail-safe Trajectory Planning for Self-driving Vehicles Using Convex Optimization Open
Ensuring the safety of self-driving vehicles is a challenging task, especially if other traffic participants severely deviate from the predicted behavior. One solution is to ensure that the vehicle is able to execute a collision-free evasi…
View article: Efficient Computation of Invariably Safe States for Motion Planning of Self-Driving Vehicles
Efficient Computation of Invariably Safe States for Motion Planning of Self-Driving Vehicles Open
Safe motion planning requires that a vehicle reaches a set of safe states at the end of the planning horizon. However, safe states of vehicles have not yet been systematically defined in the literature, nor does a computationally efficient…
View article: Efficient Mixed-Integer Programming for Longitudinal and Lateral Motion Planning of Autonomous Vehicles
Efficient Mixed-Integer Programming for Longitudinal and Lateral Motion Planning of Autonomous Vehicles Open
The application of continuous optimization to motion planning of autonomous vehicles has enjoyed increasing popularity in recent years. In order to maintain low computation times, it is advantageous to have a convex formulation, in general…