Predictive Dynamic Window Approach Development with Artificial Neural Fuzzy Inference Improvement

Teso-Fz-Betoño, Daniel; Zulueta, Ekaitz; Fernandez-Gamiz, Unai; Saenz‐Aguirre, Aitor; Martínez, Raquel

doi:10.3390/electronics8090935

Cited by 30 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiao, et al [11] presented a survey on using machine learning for motion control in mobile robot navigation: while the majority of learning approaches tackle navigation in an end-to-end manner [12], [13], it was found that approaches using learning in conjunction with other classical navigation components were more likely to have achieved better navigation performance. These methods included those that learned sub-goals [14], local planners [6]- [8], [15], [16], or planner parameters [4], [5], [9], [17]- [19]. Learning methods have also enabled navigation capabilities that complement those provided in the classical navigation literature, including terrain-aware [20]- [22] and social [23]- [25] navigation.…”

Section: A Learning For Navigationmentioning

confidence: 99%

“…Considering classical navigation systems' verifiable safety, explainability, and stable generalization to new environments, and the difficulty in fine-tuning those systems, learning adaptive planner parameters is an emerging paradigm of combining learning and planning. Examples include finding trajectory optimization coefficients using Artificial Neural Fuzzy Inference Improvement [17], optimizing two different sets of parameters for straight-line and U-turn scenarios with genetic algorithms [19], or designing novel systems that can leverage gradient descent to match expert demonstrations [18]. Recently, the APPL paradigm [4], [5], [9] has been proposed, which further allows parameters to be appropriately adjusted during deployment "on-the-fly", in order to adapt to different regions of a complex environment.…”

Section: B Adaptive Parameters For Classical Navigationmentioning

confidence: 99%

See 1 more Smart Citation

APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback

Wang,

Xiao,

Warnell

et al. 2021

Preprint

View full text Add to dashboard Cite

Classical autonomous navigation systems can control robots in a collision-free manner, oftentimes with verifiable safety and explainability. When facing new environments, however, finetuning of the system parameters by an expert is typically required before the system can navigate as expected. To alleviate this requirement, the recently-proposed Adaptive Planner Parameter Learning paradigm allows robots to learn how to dynamically adjust planner parameters using a teleoperated demonstration or corrective interventions from non-expert users. However, these interaction modalities require users to take full control of the moving robot, which requires the users to be familiar with robot teleoperation. As an alternative, we introduce APPLE, Adaptive Planner Parameter Learning from Evaluative Feedback (realtime, scalar-valued assessments of behavior), which represents a less-demanding modality of interaction. Simulated and physical experiments show APPLE can achieve better performance compared to the planner with static default parameters and even yield improvement over learned parameters from richer interaction modalities. I. INTRODUCTIONM OBILE robot navigation is a well-studied problem in the robotics community. Many classical approaches have been developed over the last several decades and several of them have been robustly deployed on physical robot platforms moving in the real world [1], [2], with verifiable guarantees of safety and explainability.However, prior to deployment in a new environment, these approaches typically require parameter re-tuning in order to achieve robust navigation performance. For example, in cluttered environments, a low velocity and high sampling rate are necessary in order for the system to be able to generate safe and smooth motions, whereas in relatively open spaces, a

show abstract

Section: A Learning For Navigationmentioning

confidence: 99%

Section: B Adaptive Parameters For Classical Navigationmentioning

confidence: 99%

APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback

Wang,

Xiao,

Warnell

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This process is commonly known as parameter tuning, which requires robotics experts' intuition, experience, or trial-anderror [1], [2]. To alleviate the burden of expert tuning, automatic tuning systems have been proposed, such as those using fuzzy logic [4] or gradient descent [5], to find one set of parameters tailored to the specific navigation scenario. Fig.…”

Section: A Parameter Tuningmentioning

confidence: 99%

“…Moreover, the performance of the Department of 1 Physics zfxu@utexas.edu, 2 Computer Science {dgauraang, xiao, bliu, pstone}@cs.utexa.edu, 3 Mathematics ani.nair@utexas.edu, 5 Electrical and Computer Engineering zizhao.wang@utexas.edu, University of Texas at Austin, Austin, Texas 78712. 4 Computational and Information Sciences Directorate, Army Research Laboratory, Adelphi, MD 20783 garrett.a.warnell.civ@mail.mil. 6 Sony AI.…”

Section: Introductionmentioning

confidence: 99%

APPLR: Adaptive Planner Parameter Learning from Reinforcement

Xu¹,

Dhamankar²,

Nair³

et al. 2020

Preprint

View full text Add to dashboard Cite

Classical navigation systems typically operate using a fixed set of hand-picked parameters (e.g. maximum speed, sampling rate, inflation radius, etc.) and require heavy expert re-tuning in order to work in new environments. To mitigate this requirement, it has been proposed to learn parameters for different contexts in a new environment using human demonstrations collected via teleoperation. However, learning from human demonstration limits deployment to the training environment, and limits overall performance to that of a potentially-suboptimal demonstrator. In this paper, we introduce APPLR, Adaptive Planner Parameter Learning from Reinforcement, which allows existing navigation systems to adapt to new scenarios by using a parameter selection scheme discovered via reinforcement learning (RL) in a wide variety of simulation environments. We evaluate APPLR on a robot in both simulated and physical experiments, and show that it can outperform both a fixed set of hand-tuned parameters and also a dynamic parameter tuning scheme learned from human demonstration.

show abstract

“…However, when facing new environments, they still need a great deal of tuning, which often requires expert robotics knowledge [6], [7]. Prior work has considered automated parameter tuning, e.g., finding trajectory optimization weights [8] for the DWA planner [2], or designing novel systems that can leverage gradient descent to match expert demonstrations [9]. Specifically, Xiao et al [10] adopted black-box optimization to automatically map a robot's local observation to the optimal planner parameters via learning from human demonstration.…”

Section: A Adaptive Parameters For Classical Navigationmentioning

confidence: 99%

APPLI: Adaptive Planner Parameter Learning From Interventions

Wang

Xiao

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

While classical autonomous navigation systems can typically move robots from one point to another safely and in a collision-free manner, these systems may fail or produce suboptimal behavior in certain scenarios. The current practice in such scenarios is to manually re-tune the system's parameters, e.g. max speed, sampling rate, inflation radius, to optimize performance. This practice requires expert knowledge and may jeopardize performance in the originally good scenarios. Meanwhile, it is relatively easy for a human to identify those failure or suboptimal cases and provide a teleoperated intervention to correct the failure or suboptimal behavior. In this work, we seek to learn from those human interventions to improve navigation performance. In particular, we propose Adaptive Planner Parameter Learning from Interventions (APPLI), in which multiple sets of navigation parameters are learned during training and applied based on a confidence measure to the underlying navigation system during deployment. In our physical experiments, the robot achieves better performance compared to the planner with static default parameters, and even dynamic parameters learned from a full human demonstration. We also show APPLI's generalizability in another unseen physical test course, and a suite of 300 simulated navigation environments.

show abstract

Predictive Dynamic Window Approach Development with Artificial Neural Fuzzy Inference Improvement

Cited by 30 publications

References 31 publications

APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback

APPLE: Adaptive Planner Parameter Learning from Evaluative Feedback

APPLR: Adaptive Planner Parameter Learning from Reinforcement

APPLI: Adaptive Planner Parameter Learning From Interventions

Contact Info

Product

Resources

About