Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Environments

Visca, Marco; Bouton, Arthur; Powell, Roger; Gao, Yang; Fallah, Saber

doi:10.1109/icra48506.2021.9560771

Cited by 13 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, the sequential context of the wheel-terrain interaction can be captured by considering the actual traverse dynamics, thereby leading to better prediction accuracy when traversing highly uneven terrains. The point cloud is preprocessed according to the method described in [24]. A diagram of the procedure is illustrated in Fig.…”

Section: Methodology a Geometric Analysis With Conv1dmentioning

confidence: 99%

“…Specifically, each row can be viewed as the terrain elevation under a section of the AMR along its width at a specific time, while each column illustrates the evolution of the terrain under a specific location of the AMR as it advances along the trajectory. For brevity of the paper, the details are referred to [24]. In our application, the voxel discretization is set to 6.25 cm × 6.25 cm, while each trajectory is 2.7 m long, resulting into a matrix x of 110 × 40 elevation values.…”

Section: Methodology a Geometric Analysis With Conv1dmentioning

confidence: 99%

“…In [24], the use of Conv1D neural networks to model complex wheel-terrain interactions over unstructured geometries and their effect on the driving energy consumption was proposed. However, predictions were performed on a single terrain type with known terramechanical properties, while possible generalization and adaptation were not considered.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we use similar implementations of [23] and [24] as main references for quantitative and qualitative comparisons. Specifically, we refer to them respectively as Meta-Plane and SingleTerrain-Conv1D (ST-Conv1D), while we refer to the method proposed in this paper as Meta-Conv1D.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Meta-Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Terrains

Visca¹,

Powell²,

Gao³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Driving energy consumption plays a major role in the navigation of autonomous mobile robots in off-road scenarios. However, real-time constraints often limit the accuracy of the energy estimations, especially in scenarios where accurate wheel-terrain interactions are complex to model. This paper reports on first results of an adaptive deep meta-learning energy-aware path planner that can provide energy estimates of a mobile robot traversing complex uneven terrains with varying and unknown terrain properties. A novel feature of the method is the integration into the meta-learning framework of a 1D convolutional neural network to analyze the terrain sequentially, in the same temporal order as it would be experienced by the robot when moving, and efficiently adapt its energy estimates to the local terrain conditions based on a small number of local measurements. The performance of the method is assessed in a 3D-body dynamic simulator over several typologies of deformable terrains and unstructured geometries. We provide evidence of the benefit of the proposed approach to retain 83% r2 score of the original simulator at 0.55% of the computing time. Finally, we compare the method with alternative state-of-the-art deep learning solutions. In this way, we show indications of its improved robustness to provide more informed energy estimations and energy-efficient paths when navigating over challenging uneven terrains.</p>

show abstract

Section: Methodology a Geometric Analysis With Conv1dmentioning

confidence: 99%

Section: Methodology a Geometric Analysis With Conv1dmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Meta-Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Terrains

Visca¹,

Powell²,

Gao³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, many areas in off-road environments contain complex, unstructured geometries, such as scattered rocks, steps, bumps, and rough terrain. Traversing unstructured geometries can induce complex motion dynamics, uncertain wheel-terrain interactions, and can pose increased challenges to the AMR locomotion and control system [13]. VOLUME 4, 2016 Such complex interplay between varying, unknown terrain properties, unstructured geometries, and its effect on the driving energy consumption, is challenging to model and is affected by considerable uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Meta-Conv1D Driving Energy Prediction for Mobile Robots in Unstructured Terrains

Visca¹,

Powell²,

Gao³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Driving energy consumption plays an important role in the navigation of autonomous mobile robots in off-road scenarios. However, the accuracy of the driving energy predictions is often affected by a high degree of uncertainty due to unknown and constantly varying terrain properties, and the complex wheel-terrain interaction in unstructured terrains. In this paper, we propose a probabilistic deep meta-learning approach to model the existing uncertainty in the driving energy consumption and efficiently adapt the probabilistic predictions based on a small number of local measurements. Our method expands upon an existing deterministic deep-meta learning model that, in contrast, only provided single-point energy estimates. The performance of our method is compared against the deterministic approach in a 3D-body dynamic simulator over several typologies of deformable terrains and unstructured geometries. In this way, we provide evidence of the benefit of the proposed method to enhance the predictions with informative probabilistic considerations, which can be crucial to the safety of mobile robots traversing challenging, unstructured environments.

show abstract

Modeling analysis and experiment for energy system of ocean energy driven unmanned marine vehicle: The Yulang II case study

Jia,

Liao,

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

It is critical to master a marine robot's energy system characteristics adequately to ensure that the robot can perform long‐endurance tasks in complex and ever‐changing marine environments. This paper presents, for the first time, an energy system modeling and analysis method for a marine robot driven by wind, solar, and wave composite energy, using Yulang II as an example. First, an onshore experiment method was designed, and then the conversion experiment of wind, sunlight, and electrical energy was carried out based on that experiment method. At the same time, based on computational fluid dynamics technology, a resistance pole curve considering wave energy capture is constructed. In addition, the attitude, relative motion, and battery constraints of the robot in the ocean are analyzed to construct the energy system model of Yulang II. Finally, the method and model proposed in this paper were compared and verified by simulation and field tests. The results indicated that the corrected forecast deviation was 5.71% in the typical marine environment of the experiment, which supported the study of ocean energy‐driven unmanned marine vehicles strongly.

show abstract

Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Environments

Cited by 13 publications

References 26 publications

Meta-Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Terrains

Meta-Conv1D Energy-Aware Path Planner for Mobile Robots in Unstructured Terrains

Probabilistic Meta-Conv1D Driving Energy Prediction for Mobile Robots in Unstructured Terrains

Modeling analysis and experiment for energy system of ocean energy driven unmanned marine vehicle: The Yulang II case study

Contact Info

Product

Resources

About