Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map

Cai, Xiaoyi; Everett, Michael; Fink, Jonathan; How, Jonathan P.

doi:10.1109/iros47612.2022.9982200

Cited by 25 publications

(16 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We notice that due to the property that pointwise converging sequences of kernels are again kernels [50,Corrollary 4.17]. Showing that K λ is a kernel thus reduces to showing that the double integral in (10)…”

Section: B Proofs Of Theoretical Resultsmentioning

confidence: 99%

“…Though powerful, forecasting dynamical systems via learned models commonly requires compositions of highly nonlinear mappings [7,8]. Therefore, it is often challenging to use such models in optimization-based decision making that relies on simulators or predictive models, e.g., reinforcement learning [9][10][11][12]. A particularly beneficial perspective for dealing with the aforementioned problem comes from Koopman operator theory [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Diffeomorphically Learning Stable Koopman Operators

Bevanda

Beier

Sebastian

et al. 2022

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e.g., the state of an agent or the reward of a policy. Forecasts of such complex phenomena are commonly described by highly nonlinear dynamical systems, making their use in optimization-based decision-making challenging. Koopman operator theory offers a beneficial paradigm for addressing this problem by characterizing forecasts via linear dynamical systems. This makes system analysis and long-term predictions simple -involving only matrix multiplications. However, the transformation to a linear system is generally non-trivial and unknown, requiring learning-based approaches. While there exists a variety of approaches, they usually lack crucial learning-theoretic guarantees, such that the behavior of the obtained models with increasing data and dimensionality is often unclear. We address the aforementioned by deriving a novel reproducing kernel Hilbert space (RKHS) that solely spans transformations into linear dynamical systems. The resulting Koopman Kernel Regression (KKR) framework enables the use of statistical learning tools from function approximation for novel convergence results and generalization risk bounds under weaker assumptions than existing work. Our numerical experiments indicate advantages over state-of-the-art statistical learning approaches for Koopman-based predictors.

show abstract

Section: B Proofs Of Theoretical Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Diffeomorphically Learning Stable Koopman Operators

Bevanda

Beier

Sebastian

et al. 2022

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

show abstract

“…To navigate a vehicle in off-road environments, a motion planner can leverage the perceived terrain features to plan safe and efficient trajectories. The terrain features are usually converted into costs for a planner to rank and assess the risk of trajectories [5,6,10,13,14]. In our experiments, we illustrate how to use the MPPI planner [47] for motion planning with terrain features and robot capability considered.…”

Section: Related Workmentioning

confidence: 99%

TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation

Meng¹,

Lambert²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Effective use of camera-based vision systems is essential for robust performance in autonomous off-road driving, particularly in the high-speed regime. Despite success in structured, on-road settings, current end-to-end approaches for scene prediction have yet to be successfully adapted for complex outdoor terrain. To this end, we present TerrainNet, a visionbased terrain perception system for semantic and geometric terrain prediction for aggressive, off-road navigation. The approach relies on several key insights and practical considerations for achieving reliable terrain modeling. The network includes a multi-headed output representation to capture fine-and coarsegrained terrain features necessary for estimating traversability. Accurate depth estimation is achieved using self-supervised depth completion with multi-view RGB and stereo inputs. Requirements for real-time performance and fast inference speeds are met using efficient, learned image feature projections. Furthermore, the model is trained on a large-scale, real-world off-road dataset collected across a variety of diverse outdoor environments. We show how TerrainNet can also be used for costmap prediction and provide a detailed framework for integration into a planning module. We demonstrate the performance of TerrainNet through extensive comparison to current state-of-the-art baselines for camera-only scene prediction. Finally, we showcase the effectiveness of integrating TerrainNet within a complete autonomousdriving stack by conducting a real-world vehicle test in a challenging off-road scenario.

show abstract

“…While these studies focus on either collision avoidance [24], [25], classification-based traversability modeling [26], or a single-modal risk behavior [27], our focus is on handling the immobilization risk that requires continuous and multi-modal modeling of rover slip on various kinds of deformable terrains. Risk-aware off-road navigation by Cai et al [28] uses CVaR to estimate pessimistic robot speed in environments with dirt and vegetation. Although their use of CVaR for velocity prediction is similar to ours, their semantic-based scene understanding without considering terrain geometry is unsuitable for capturing the immobilization risk owing to rugged celestial surfaces.…”

Section: Related Workmentioning

confidence: 99%

“…Compared to existing planners for planetary rover navigation [19]- [23], our method simultaneously considers multi-modal slip behaviors due to heterogeneous terrains and the immobilization risk. The proposed solution (i.e., MGP-based traversability model integrating visual and geometric information as well as CVaR-based continuous (non-boolean) risk assessment) addresses challenges that are only partly handled by existing CVaR-based risk-aware planners in other areas [24]- [28].…”

Section: Related Workmentioning

confidence: 99%

Active Traversability Learning via Risk-Aware Information Gathering for Planetary Exploration Rovers

Endo

Ishigami

2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Machine learning (ML) plays a crucial role in assessing traversability for autonomous rover operations on deformable terrains but suffers from inevitable prediction errors. Especially for heterogeneous terrains where the geological features vary from place to place, erroneous traversability prediction can become more apparent, increasing the risk of unrecoverable rover's wheel slip and immobilization. In this work, we propose a new path planning algorithm that explicitly accounts for such erroneous prediction. The key idea is the probabilistic fusion of distinctive ML models for terrain type classification and slip prediction into a single distribution. This gives us a multimodal slip distribution accounting for heterogeneous terrains and further allows statistical risk assessment to be applied to derive risk-aware traversing costs for path planning. Extensive simulation experiments have demonstrated that the proposed method is able to generate more feasible paths on heterogeneous terrains compared to existing methods.

show abstract

Risk-Aware Off-Road Navigation via a Learned Speed Distribution Map

Cited by 25 publications

References 33 publications

Diffeomorphically Learning Stable Koopman Operators

Diffeomorphically Learning Stable Koopman Operators

TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation

Active Traversability Learning via Risk-Aware Information Gathering for Planetary Exploration Rovers

Contact Info

Product

Resources

About