\n \n \n
\n\n\n
\n
\n\n \n \n \n \n \n \n Optimization-based Fault Mitigation for Safe Automated Driving.\n \n \n \n \n\n\n \n Lodder, N,; van der Ploeg, C.; Ferranti, L.; and Silvas, E.\n\n\n \n\n\n\n In
IFAC World Congress, Japan, 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{lodder_n_optimization-based_2023,\n\taddress = {Japan},\n\ttitle = {Optimization-based {Fault} {Mitigation} for {Safe} {Automated} {Driving}},\n\turl = {paper=https://arxiv.org/pdf/2303.18165.pdf},\n\tabstract = {With increased developments and interest in cooperative driving and higher levels of automation (SAE level 3+), the need for safety systems that are capable to monitor system health and maintain safe operations in faulty scenarios is increasing. A variety of faults or failures could occur, and there exists a high variety of ways to respond to such events. Once a fault or failure is detected, there is a need to classify its severity and decide on appropriate and safe mitigating actions. To provide a solution to this mitigation challenge, in this paper a functional-safety architecture is proposed and an optimization-based mitigation algorithm is introduced. This algorithm uses nonlinear model predictive control (NMPC) to bring a vehicle, suffering from a severe fault, such as a power steering failure, to a safe-state. The internal model of the NMPC uses the information from the fault detection, isolation and\nidentification to optimize the tracking performance of the controller, showcasing the need of the proposed architecture. Given a string of ACC vehicles, our results demonstrate a variety of tactical decisionmaking approaches that a fault-affected vehicle could employ to manage any faults. Furthermore,\nwe show the potential for improving the safety of the affected vehicle as well as the effect of these approaches on the duration of the manoeuvre.},\n\tbooktitle = {{IFAC} {World} {Congress}},\n\tauthor = {{Lodder, N,} and {van der Ploeg, C.} and {Ferranti, L.} and {Silvas, E.}},\n\tyear = {2023},\n\tkeywords = {key\\_automotive, key\\_control, key\\_fault\\_tolerant, key\\_mpc},\n}\n\n
\n
\n\n\n
\n With increased developments and interest in cooperative driving and higher levels of automation (SAE level 3+), the need for safety systems that are capable to monitor system health and maintain safe operations in faulty scenarios is increasing. A variety of faults or failures could occur, and there exists a high variety of ways to respond to such events. Once a fault or failure is detected, there is a need to classify its severity and decide on appropriate and safe mitigating actions. To provide a solution to this mitigation challenge, in this paper a functional-safety architecture is proposed and an optimization-based mitigation algorithm is introduced. This algorithm uses nonlinear model predictive control (NMPC) to bring a vehicle, suffering from a severe fault, such as a power steering failure, to a safe-state. The internal model of the NMPC uses the information from the fault detection, isolation and identification to optimize the tracking performance of the controller, showcasing the need of the proposed architecture. Given a string of ACC vehicles, our results demonstrate a variety of tactical decisionmaking approaches that a fault-affected vehicle could employ to manage any faults. Furthermore, we show the potential for improving the safety of the affected vehicle as well as the effect of these approaches on the duration of the manoeuvre.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Scenario-Based Motion Planning with Bounded Probability of Collision.\n \n \n \n \n\n\n \n de Groot, O.; Ferranti, L.; Gavrila, D. M.; and Alonso-Mora, J.\n\n\n \n\n\n\n 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Video\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@misc{de_groot_scenario-based_2023,\n\ttitle = {Scenario-{Based} {Motion} {Planning} with {Bounded} {Probability} of {Collision}},\n\turl = {paper=https://arxiv.org/pdf/2307.01070.pdf video=https://www.youtube.com/watch?v=-rqoTICmEO4},\n\tabstract = {Robots will increasingly operate near humans that introduce uncertainties in the motion planning problem due to their complex nature. Typically, chance constraints are introduced in the planner to optimize performance while guaranteeing probabilistic safety. However, existing methods do not consider the actual probability of collision for the planned trajectory, but rather its marginalization, that is, the independent collision probabilities for each planning step and/or dynamic obstacle, resulting in conservative trajectories. To address this issue, we introduce a novel real-time capable method termed Safe Horizon MPC, that explicitly constrains the joint probability of collision with all obstacles over the duration of the motion plan. This is achieved by reformulating the chance-constrained planning problem using scenario optimization and predictive control. Our method is less conservative than state-of-the-art approaches, applicable to arbitrary probability distributions of the obstacles' trajectories, computationally tractable and scalable. We demonstrate our proposed approach using a mobile robot and an autonomous vehicle in an environment shared with humans},\n\tauthor = {de Groot, O. and Ferranti, L. and Gavrila, D. M. and Alonso-Mora, J.},\n\tyear = {2023},\n\tkeywords = {key\\_collision\\_avoidance, key\\_control, key\\_motion\\_planning, key\\_mpc},\n}\n\n
\n
\n\n\n
\n Robots will increasingly operate near humans that introduce uncertainties in the motion planning problem due to their complex nature. Typically, chance constraints are introduced in the planner to optimize performance while guaranteeing probabilistic safety. However, existing methods do not consider the actual probability of collision for the planned trajectory, but rather its marginalization, that is, the independent collision probabilities for each planning step and/or dynamic obstacle, resulting in conservative trajectories. To address this issue, we introduce a novel real-time capable method termed Safe Horizon MPC, that explicitly constrains the joint probability of collision with all obstacles over the duration of the motion plan. This is achieved by reformulating the chance-constrained planning problem using scenario optimization and predictive control. Our method is less conservative than state-of-the-art approaches, applicable to arbitrary probability distributions of the obstacles' trajectories, computationally tractable and scalable. We demonstrate our proposed approach using a mobile robot and an autonomous vehicle in an environment shared with humans\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Globally Guided Trajectory Planning in Dynamic Environments.\n \n \n \n \n\n\n \n de Groot, O.; Ferranti, L.; Gavrila, D. M.; and Alonso-Mora, J.\n\n\n \n\n\n\n In
2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK, 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Video\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{de_groot_o_globally_2023,\n\taddress = {London, UK},\n\ttitle = {Globally {Guided} {Trajectory} {Planning} in {Dynamic} {Environments}},\n\turl = {paper=https://r2clab.com/wp-content/uploads/2023/03/ICRA2023_homotopy-3.pdf video=https://www.youtube.com/watch?v=tkRbsAuSTrA},\n\tabstract = {Navigating mobile robots through environments shared with humans is challenging. From the perspective of the robot, humans are dynamic obstacles that must be avoided. These obstacles make the collision-free space nonconvex, which leads to two distinct passing behaviors per obstacle (passing left or right). For local planners, such as receding-horizon trajectory optimization, each behavior presents a local optimum in which the planner can get stuck. This may result in slow or unsafe motion even when a better plan exists. In this work, we identify trajectories for multiple locally optimal driving\nbehaviors, by considering their topology. This identification is made consistent over successive iterations by propagating the\ntopology information. The most suitable high-level trajectory\nguides a local optimization-based planner, resulting in fast and\nsafe motion plans.We validate the proposed planner on a mobile\nrobot in simulation and real-world experiments.},\n\tbooktitle = {2023 {IEEE} {International} {Conference} on {Robotics} and {Automation} ({ICRA})},\n\tauthor = {{de Groot, O.} and {Ferranti, L.} and {Gavrila, D. M.} and {Alonso-Mora, J.}},\n\tyear = {2023},\n\tkeywords = {key\\_collision\\_avoidance, key\\_motion\\_planning, key\\_mpc},\n}\n\n
\n
\n\n\n
\n Navigating mobile robots through environments shared with humans is challenging. From the perspective of the robot, humans are dynamic obstacles that must be avoided. These obstacles make the collision-free space nonconvex, which leads to two distinct passing behaviors per obstacle (passing left or right). For local planners, such as receding-horizon trajectory optimization, each behavior presents a local optimum in which the planner can get stuck. This may result in slow or unsafe motion even when a better plan exists. In this work, we identify trajectories for multiple locally optimal driving behaviors, by considering their topology. This identification is made consistent over successive iterations by propagating the topology information. The most suitable high-level trajectory guides a local optimization-based planner, resulting in fast and safe motion plans.We validate the proposed planner on a mobile robot in simulation and real-world experiments.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Learning Players' Objectives in Continuous Dynamic Games from Partial State Observations.\n \n \n \n \n\n\n \n Peters, L.; Rubies-Royo, Vicenç; Tomlin, C. J; Ferranti, L.; Alonso-Mora, J.; Stachniss, C.; and Fridovich-Keil, D\n\n\n \n\n\n\n
International Journal of Robotics Research. 2023.\n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@article{peters_l_learning_2023,\n\ttitle = {Learning {Players}' {Objectives} in {Continuous} {Dynamic} {Games} from {Partial} {State} {Observations}},\n\turl = {paper=https://arxiv.org/pdf/2302.01999.pdf},\n\tabstract = {Robots deployed to the real world must be able to interact with other agents in their environment. Dynamic game theory provides a powerful mathematical framework for modeling scenarios in which agents have individual objectives and interactions evolve over time. However, a key limitation of such techniques is that they require a-priori knowledge of all players' objectives. In this work, we address this issue by proposing a novel method for learning players' objectives in continuous dynamic games from noise-corrupted, partial state observations. Our approach learns objectives by coupling the estimation of unknown cost parameters of each player with inference of unobserved states and inputs through Nash equilibrium constraints. By coupling past state estimates with future state predictions, our approach is amenable to simultaneous online learning and prediction in receding horizon fashion. We demonstrate our method in several simulated traffic scenarios in which we recover players' preferences for, e.g., desired travel speed and collision-avoidance behavior. Results show that our method reliably estimates game-theoretic models from noise-corrupted data that closely matches ground-truth objectives, consistently outperforming state-of-the-art approaches.},\n\tjournal = {International Journal of Robotics Research},\n\tauthor = {{Peters, L.} and {Rubies-Royo, Vicenç} and {Tomlin, C. J} and {Ferranti, L.} and {Alonso-Mora, J.} and Stachniss, C. and Fridovich-Keil, D},\n\tyear = {2023},\n}\n\n
\n
\n\n\n
\n Robots deployed to the real world must be able to interact with other agents in their environment. Dynamic game theory provides a powerful mathematical framework for modeling scenarios in which agents have individual objectives and interactions evolve over time. However, a key limitation of such techniques is that they require a-priori knowledge of all players' objectives. In this work, we address this issue by proposing a novel method for learning players' objectives in continuous dynamic games from noise-corrupted, partial state observations. Our approach learns objectives by coupling the estimation of unknown cost parameters of each player with inference of unobserved states and inputs through Nash equilibrium constraints. By coupling past state estimates with future state predictions, our approach is amenable to simultaneous online learning and prediction in receding horizon fashion. We demonstrate our method in several simulated traffic scenarios in which we recover players' preferences for, e.g., desired travel speed and collision-avoidance behavior. Results show that our method reliably estimates game-theoretic models from noise-corrupted data that closely matches ground-truth objectives, consistently outperforming state-of-the-art approaches.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n EValueAction: a proposal for policy evaluation in simulation to support interactive imitation learning.\n \n \n \n \n\n\n \n Sibona, F.; Luijkx, J.; van der Heijden, B.; Ferranti, L.; and Indri, M.\n\n\n \n\n\n\n In
IEEE INDIN 2023, 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 3 downloads\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n\n\n\n
\n
@inproceedings{sibona_evalueaction_2023,\n\ttitle = {{EValueAction}: a proposal for policy evaluation in simulation to support interactive imitation learning},\n\turl = {paper=https://r2clab.com/wp-content/uploads/2023/06/Paper_EVA_2023_acks.pdf},\n\tabstract = {The up-and-coming concept of Industry 5.0 foresees\nhuman-centric flexible production lines, where collaborative\nrobots support human workforce. In order to allow a seamless\ncollaboration between intelligent robots and human workers,\ndesigning solutions for non-expert users is crucial. Learning from\ndemonstration emerged as the enabling approach to address such\na problem. However, more focus should be put on finding safe\nsolutions which optimize the cost associated with the demonstrations\ncollection process. This paper introduces a preliminary outline\nof a system, namely EValueAction (EVA), designed to assist\nthe human in the process of collecting interactive demonstrations\ntaking advantage of simulation to safely avoid failures. A policy\nis pre-trained with human-demonstrations and, where needed,\nnew informative data are interactively gathered and aggregated\nto iteratively improve the initial policy. A trial case study further\nreinforces the relevance of the work by demonstrating the crucial\nrole of informative demonstrations for generalization.},\n\tbooktitle = {{IEEE} {INDIN} 2023},\n\tauthor = {Sibona, F. and Luijkx, J. and van der Heijden, B. and Ferranti, L. and Indri, M.},\n\tyear = {2023},\n}\n\n
\n
\n\n\n
\n The up-and-coming concept of Industry 5.0 foresees human-centric flexible production lines, where collaborative robots support human workforce. In order to allow a seamless collaboration between intelligent robots and human workers, designing solutions for non-expert users is crucial. Learning from demonstration emerged as the enabling approach to address such a problem. However, more focus should be put on finding safe solutions which optimize the cost associated with the demonstrations collection process. This paper introduces a preliminary outline of a system, namely EValueAction (EVA), designed to assist the human in the process of collecting interactive demonstrations taking advantage of simulation to safely avoid failures. A policy is pre-trained with human-demonstrations and, where needed, new informative data are interactively gathered and aggregated to iteratively improve the initial policy. A trial case study further reinforces the relevance of the work by demonstrating the crucial role of informative demonstrations for generalization.\n
\n\n\n
\n\n\n
\n
\n\n \n \n \n \n \n \n Curvature-Aware Model Predictive Contouring Control.\n \n \n \n \n\n\n \n Lyons, L.; and Ferranti, L.\n\n\n \n\n\n\n In
2023 IEEE International Conference on Robotics and Automation (ICRA), 2023. \n
\n\n
\n\n
\n\n
\n\n \n \n Paper\n \n \n \n Video\n \n \n\n \n\n \n link\n \n \n\n bibtex\n \n\n \n \n \n abstract \n \n\n \n \n \n 19 downloads\n \n \n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@inproceedings{lyons_l_curvature-aware_2023,\n\ttitle = {Curvature-{Aware} {Model} {Predictive} {Contouring} {Control}},\n\turl = {paper=https://r2clab.com/wp-content/uploads/2023/02/Lyons_ICRA_2023.pdf video=https://www.youtube.com/watch?v=6-E3I99D2sc},\n\tabstract = {We present a novel Curvature-Aware Model Predictive Contouring Control (CA-MPCC) formulation for mobile\nrobotics motion planning. Our method aims at generalizing\nthe traditional contouring control formulation derived from\nmachining to autonomous driving applications. The proposed\ncontroller is able of handling sharp curvatures in the reference\npath while subject to non-linear constraints, such as lane\nboundaries and dynamic obstacle collision avoidance. Compared to a standard MPCC formulation, our method improves\nthe reliability of the path-following algorithm and simplifies the\ntuning, while preserving real-time capabilities. We validate our\nfindings in both simulations and experiments on a scaled-down\ncar-like robot.},\n\tbooktitle = {2023 {IEEE} {International} {Conference} on {Robotics} and {Automation} ({ICRA})},\n\tauthor = {{Lyons, L.} and {Ferranti, L.}},\n\tyear = {2023},\n\tkeywords = {key\\_automotive, key\\_collision\\_avoidance, key\\_motion\\_planning, key\\_mpc},\n}\n\n
\n
\n\n\n
\n We present a novel Curvature-Aware Model Predictive Contouring Control (CA-MPCC) formulation for mobile robotics motion planning. Our method aims at generalizing the traditional contouring control formulation derived from machining to autonomous driving applications. The proposed controller is able of handling sharp curvatures in the reference path while subject to non-linear constraints, such as lane boundaries and dynamic obstacle collision avoidance. Compared to a standard MPCC formulation, our method improves the reliability of the path-following algorithm and simplifies the tuning, while preserving real-time capabilities. We validate our findings in both simulations and experiments on a scaled-down car-like robot.\n
\n\n\n
\n\n\n\n\n\n