Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains

Visca, Marco

doi:10.36227/techrxiv.14812905

Cited by 5 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other works have proposed the use of meta-learning for the online adaptation of robotic platforms [20]- [22]. In [23], an energy-aware deep meta-learning framework to predict, adapt, and plan over terrains with unknown and varying terramechanical properties was proposed. However, the prediction model considered the inclination of the terrain as the only important geometric factor for the estimation of the driving energy.…”

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%

“…In the black-box formulation, f θ is a single neural network trained in an end-to-end fashion to predict y ts j from x ts j and D tr . For more information on the meta-learning black-box formulation refer to [23].…”

Section: B Meta-learning Preliminariesmentioning

confidence: 99%

“…Finally, in line with the Meta-Plane and ST-Conv1D methods in [23] [24], we adopt the A* algorithm to optimize the path according to the driving energy consumption in the state-lattice space [28]. A*-like graph search methods have the advantage to guarantee bounded path optimality, and to reduce the computing cost of planning by making use of heuristics [29].…”

Section: Path Planning Integrationmentioning

confidence: 99%

“…A*-like graph search methods have the advantage to guarantee bounded path optimality, and to reduce the computing cost of planning by making use of heuristics [29]. In this work, we adopt the same heuristic function H as in [23] [24]. Specifically, we define H(n, t) = max[0, (Gθ + β)d], where θ and d are respectively the relative inclination in degree and euclidean distance in meters between the current node n and the target t, while G and β are heuristic parameters set to provide globally optimistic energy estimates for all available terrain types.…”

Section: Path Planning Integrationmentioning

confidence: 99%

See 4 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: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: B Meta-learning Preliminariesmentioning

confidence: 99%

Section: Path Planning Integrationmentioning

confidence: 99%

Section: Path Planning Integrationmentioning

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

show abstract

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

et al. 2022

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, a probabilistic deep meta-learning approach is proposed to model the existing uncertainty in the driving energy consumption and efficiently adapt the probabilistic predictions based on a small number of local measurements. The method expands upon an existing deterministic deep-meta learning model that, in contrast, only provided single-point energy estimates. The performance of the proposed 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, the benefits of the proposed method are illustrated to enhance the predictions with informative probabilistic considerations, which can be crucial to the safety of mobile robots traversing challenging, unstructured environments.INDEX TERMS Autonomous mobile robots, deep learning, energy-aware path planning, meta-learning, probabilistic neural networks

show abstract

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

Deep Meta-Learning Energy-Aware Path Planner for Unmanned Ground Vehicles in Unknown Terrains

Cited by 5 publications

References 23 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

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

Contact Info

Product

Resources

About