L. Knödler
Please Note
9 records found
1
Control Barrier Functions (CBFs) have proven to be an effective tool for performing safe control synthesis for nonlinear systems. However, guaranteeing safety in the presence of disturbances and input constraints for high relative degree systems is a difficult problem. In this work, we propose the Robust Policy CBF (RPCBF), a practical approach for constructing robust CBF approximations online via the estimation of a value function. We establish conditions under which the approximation qualifies as a valid CBF and demonstrate the effectiveness of the RPCBF-safety filter in simulation on a variety of high relative degree input-constrained systems. Finally, we demonstrate the benefits of our method in compensating for model errors on a hardware quadcopter platform by treating the model errors as disturbances.
We first examine the standard approach of splitting local motion planning into two sub-problems: predicting human trajectories and solving constrained trajectory optimization to avoid collisions. While this approach provides safety guarantees and can handle uncertainties, it neglects the interactions between the robot and the humans. We address this by formulating a Model Predictive Control problem in which the robot’s action influences both its own state and the human states. Focusing on navigation among pedestrians, we leverage the interpretable and established Social Force Model (SFM) to model the human response dynamics to robot actions. By accounting for the robot’s influence on pedestrian behavior, we demonstrate that the robot can guide pedestrian behavior. However, a carefully designed cost function is essential to promote cooperation and prevent exploitation.
Next, we focus on the limitations of learning-based approaches that can address social compliance, specifically, Imitation Learning (IL). While IL enables the learning of socially compliant behaviors from demonstrations or observations, the resulting policy lacks formal safety guarantees. Safety filters based on, e.g., Control Barrier Functions (CBFs), adapt control inputs to ensure safety and can be combined with IL policies. While CBFs are an effective tool to certify safety, two challenges remain: constructing them for complex systems with input constraints and accounting for model uncertainties. We propose Robust Policy Control Barrier Functions, a method for constructing robust CBFs that guarantees safety under worst-case bounded disturbances. Furthermore, we present a practical approximation and demonstrate its effectiveness in simulation and hardware experiments.
Next, we focus on adaptability, specifically in data-driven pedestrian prediction models, which are crucial for the decoupled prediction and planning approach. While existing models are trained offline on general datasets, they may not reflect the behavior of pedestrians in the robot’s environment. To address this, we propose a self-supervised continual learning framework that refines models during deployment using online data from the robot’s perception pipeline, preserving prior knowledge through regularization and selective retraining. Experiments show improved performance compared to naive online training. Although we focus on pedestrian prediction, the approach could extend to other methods applying learning-from-observations.
In summary, this thesis integrates interaction awareness into decoupled motion planning by leveraging the established SFM, presents a method for constructing safety filters using practical approximations of robust CBFs, and develops a framework that addresses adaptability through self-supervised continual learning. Integrating the safety filter with a socially compliant, interaction-aware policy learned from observations and adapted online through continual learning offers a comprehensive solution.
This combination could pave the way for local motion planning that is interaction-aware, safe, socially compliant, and adaptive. ...
We first examine the standard approach of splitting local motion planning into two sub-problems: predicting human trajectories and solving constrained trajectory optimization to avoid collisions. While this approach provides safety guarantees and can handle uncertainties, it neglects the interactions between the robot and the humans. We address this by formulating a Model Predictive Control problem in which the robot’s action influences both its own state and the human states. Focusing on navigation among pedestrians, we leverage the interpretable and established Social Force Model (SFM) to model the human response dynamics to robot actions. By accounting for the robot’s influence on pedestrian behavior, we demonstrate that the robot can guide pedestrian behavior. However, a carefully designed cost function is essential to promote cooperation and prevent exploitation.
Next, we focus on the limitations of learning-based approaches that can address social compliance, specifically, Imitation Learning (IL). While IL enables the learning of socially compliant behaviors from demonstrations or observations, the resulting policy lacks formal safety guarantees. Safety filters based on, e.g., Control Barrier Functions (CBFs), adapt control inputs to ensure safety and can be combined with IL policies. While CBFs are an effective tool to certify safety, two challenges remain: constructing them for complex systems with input constraints and accounting for model uncertainties. We propose Robust Policy Control Barrier Functions, a method for constructing robust CBFs that guarantees safety under worst-case bounded disturbances. Furthermore, we present a practical approximation and demonstrate its effectiveness in simulation and hardware experiments.
Next, we focus on adaptability, specifically in data-driven pedestrian prediction models, which are crucial for the decoupled prediction and planning approach. While existing models are trained offline on general datasets, they may not reflect the behavior of pedestrians in the robot’s environment. To address this, we propose a self-supervised continual learning framework that refines models during deployment using online data from the robot’s perception pipeline, preserving prior knowledge through regularization and selective retraining. Experiments show improved performance compared to naive online training. Although we focus on pedestrian prediction, the approach could extend to other methods applying learning-from-observations.
In summary, this thesis integrates interaction awareness into decoupled motion planning by leveraging the established SFM, presents a method for constructing safety filters using practical approximations of robust CBFs, and develops a framework that addresses adaptability through self-supervised continual learning. Integrating the safety filter with a socially compliant, interaction-aware policy learned from observations and adapted online through continual learning offers a comprehensive solution.
This combination could pave the way for local motion planning that is interaction-aware, safe, socially compliant, and adaptive.
As robots shift from industrial to human-centered spaces, adopting mobile manipulators, which expand workspace capabilities, becomes crucial. In these settings, seamless interaction with humans necessitates compliant control. Two common methods for safe interaction, admittance, and impedance control, require force or torque sensors, often absent in lower-cost or lightweight robots. This paper presents an adaption of impedance control that can be used on current-controlled robots without the use of force or torque sensors and shows its application for compliant control of a mobile manipulator. A calibration method is designed that enables estimation of the actuators' current/torque ratios and frictions, used by the adapted impedance controller, and that can handle model errors. The calibration method and the performance of the designed controller are experimentally validated using the Kinova GEN3 Lite arm. Results show that the calibration method is consistent and that the designed controller for the arm is compliant while also being able to track targets with five-millimeter precision when no interaction is present. Additionally, this paper presents two operational modes for interacting with the mobile manipulator: one for guiding the robot around the workspace through interacting with the arm and another for executing a tracking task, both maintaining compliance to external forces. These operational modes were tested in real-world experiments, affirming their practical applicability and effectiveness.Code: https://github.com/tud-amr/mobile-manipulator-compliance
Control Barrier Functions (CBFs) that provide formal safety guarantees have been widely used for safety-critical systems. However, it is non-trivial to design a CBF. Utilizing neural networks as CBFs has shown great success, but it necessitates their certification as CBFs. In this work, we leverage bound propagation techniques and the Branch-and - Bound scheme to efficiently verify that a neural network satisfies the conditions to be a CBF over the continuous state space. To accelerate training, we further present a framework that embeds the verification scheme into the training loop to synthesize and verify a neural CBF simultaneously. In partic-ular, we employ the verification scheme to identify partitions of the state space that are not guaranteed to satisfy the CBF conditions and expand the training dataset by incorporating additional data from these partitions. The neural network is then optimized using the augmented dataset to meet the CBF conditions. We show that for a non-linear control-affine system, our framework can efficiently certify a neural network as a CBF and render a larger safe set than state-of-the-art neural CBF works. We further employ our learned neural CBF to derive a safe controller to illustrate the practical use of our framework.
This paper studies the multi-robot task assignment problem in which a fleet of dispersed robots needs to efficiently transport a set of dynamically appearing packages from their initial locations to corresponding destinations within prescribed time-windows. Each robot can carry multiple packages simultaneously within its capacity. Given a sufficiently large robot fleet, the objective is to minimize the robots' total travel time to transport the packages within their respective time-window constraints. The problem is shown to be NP-hard, and we design two group-based distributed auction algorithms to solve this task assignment problem. Guided by the auction algorithms, robots first distributively calculate feasible package groups that they can serve, and then communicate to find an assignment of package groups. We quantify the potential of the algorithms with respect to the number of employed robots and the capacity of the robots by considering the robots' total travel time to transport all packages. Simulation results show that the designed algorithms are competitive compared with an exact centralized Integer Linear Program representation solved with the commercial solver Gurobi, and superior to popular greedy algorithms and a heuristic distributed task allocation method.
Autonomous mobile robots require accurate human motion predictions to safely and efficiently navigate among pedestrians, whose behavior may adapt to environmental changes. This paper introduces a self-supervised continual learning framework to improve data-driven pedestrian prediction models online across various scenarios continuously. In particular, we exploit online streams of pedestrian data, commonly available from the robot's detection and tracking pipelines, to refine the prediction model and its performance in unseen scenarios. To avoid the forgetting of previously learned concepts, a problem known as catastrophic forgetting, our framework includes a regularization loss to penalize changes of model parameters that are important for previous scenarios and retrains on a set of previous examples to retain past knowledge. Experimental results on real and simulation data show that our approach can improve prediction performance in unseen scenarios while retaining knowledge from seen scenarios when compared to naively training the prediction model online.