We present a sampling-based control approach that can generate smooth actions for general nonlinear systems without external smoothing algorithms. Model Predictive Path Integral (MPPI) control has been utilized in numerous robotic applications due to its appealing characteristics to solve nonconvex optimization problems. However, the stochastic nature of sampling-based methods can cause significant chattering in the resulting commands. Chattering becomes more prominent in cases where the environment changes rapidly, possibly even causing the MPPI to diverge. To address this issue, we propose a method that seamlessly combines MPPI with an input-lifting strategy. In addition, we introduce a new action cost to smooth control sequence during trajectory rollouts while preserving the information theoretic interpretation of MPPI, which was derived from non-affine dynamics. We validate our method in two nonlinear control tasks with neural network dynamics: a pendulum swing-up task and a challenging autonomous driving task. The experimental results demonstrate that our method outperforms the MPPI baselines with additionally applied smoothing algorithms.
Precise estimations of the roll and sideslip angles of autonomous vehicles are essential for autonomous driving, which requires further information about the vehicle state. As such, novel deep learning approaches have been introduced for this purpose. However, the majority of deep learning works focusing on vehicle dynamics estimations have yet to delve into learning strategies specifically for this task. Here, we argue that simply applying an adequate learning strategy to the task can boost the estimation performance. In this paper, we propose a simple yet effective curriculum learning strategy for better estimations of the roll and sideslip angles simultaneously. In addition, we compare our curriculum using a self-taught scoring function with a curriculum sorted by prior human knowledge, demonstrating its superiority. The proposed method outperforms the non-curriculum method by a large margin (up to a 16.5% decrease for sideslip as validation and 3.7% on a test), especially with regard to cornering (up to a 4% decrease). INDEX TERMSCurriculum learning, deep learning based estimator, roll angle, sensor fusion, sideslip angle, vehicle pose estimation.
Neural networks have been increasingly employed in Model Predictive Controller (MPC) to control nonlinear dynamic systems. However, MPC still poses a problem that an achievable update rate is insufficient to cope with model uncertainty and external disturbances. In this paper, we present a novel control scheme that can design an optimal tracking controller using the neural network dynamics of the MPC, making it possible to be applied as a plug-and-play extension for any existing model-based feedforward controller. We also describe how our method handles a neural network containing history information, which does not follow a general form of dynamics. The proposed method is evaluated by its performance in classical control benchmarks with external disturbances. We also extend our control framework to be applied in an aggressive autonomous driving task with unknown friction. In all experiments, our method outperformed the compared methods by a large margin. Our controller also showed low control chattering levels, demonstrating that our feedback controller does not interfere with the optimal command of MPC. 1
Traversability estimation for mobile robots in off-road environments requires more than conventional semantic segmentation used in constrained environments like on-road conditions. Recently, approaches to learning a traversability estimation from past driving experiences in a self-supervised manner are arising as they can significantly reduce human labeling costs and labeling errors. However, the self-supervised data only provide supervision for the actually traversed regions, resulting in epistemic uncertainty due to the lack of knowledge on non-traversable regions, also referred to as negative data. Negative data can rarely be collected as the system can be severely damaged while logging the data. To mitigate the uncertainty in the estimation, we introduce a deep metric learning-based method to incorporate unlabeled data with a few positive and negative prototypes. Our method jointly learns binary segmentation that reduces uncertainty in addition to the regression of traversability. To firmly evaluate the proposed framework, we introduce a new evaluation metric that comprehensively evaluates the segmentation and regression. Additionally, we construct a driving dataset 'Dtrail' in off-road environments with a mobile robot platform, which is composed of numerous complex and diverse representations of off-road environments. We examine our method on Dtrail as well as the publicly available SemanticKITTI dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.