skip to main content

This content will become publicly available on March 22, 2025

Title: Boundary-aware value function generation for safe stochastic motion planning

Navigation safety is critical for many autonomous systems such as self-driving vehicles in an urban environment. It requires an explicit consideration of boundary constraints that describe the borders of any infeasible, non-navigable, or unsafe regions. We propose a principled boundary-aware safe stochastic planning framework with promising results. Our method generates a value function that can strictly distinguish the state values between free (safe) and non-navigable (boundary) spaces in the continuous state, naturally leading to a safe boundary-aware policy. At the core of our solution lies a seamless integration of finite elements and kernel-based functions, where the finite elements allow us to characterize safety-critical states’ borders accurately, and the kernel-based function speeds up computation for the non-safety-critical states. The proposed method was evaluated through extensive simulations and demonstrated safe navigation behaviors in mobile navigation tasks. Additionally, we demonstrate that our approach can maneuver safely and efficiently in cluttered real-world environments using a ground vehicle with strong external disturbances, such as navigating on a slippery floor and against external human intervention.

more » « less
Author(s) / Creator(s):
 ;  ;  ;  ;  
Publisher / Repository:
SAGE Publications
Date Published:
Journal Name:
The International Journal of Robotics Research
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. We propose a diffusion approximation method to the continuous-state Markov decision processes that can be utilized to address autonomous navigation and control in unstructured off-road environments. In contrast to most decision-theoretic planning frameworks that assume fully known state transition models, we design a method that eliminates such a strong assumption that is often extremely difficult to engineer in reality. We first take the second-order Taylor expansion of the value function. The Bellman optimality equation is then approximated by a partial differential equation, which only relies on the first and second moments of the transition model. By combining the kernel representation of the value function, we design an efficient policy iteration algorithm whose policy evaluation step can be represented as a linear system of equations characterized by a finite set of supporting states. We first validate the proposed method through extensive simulations in 2 D obstacle avoidance and 2.5 D terrain navigation problems. The results show that the proposed approach leads to a much superior performance over several baselines. We then develop a system that integrates our decision-making framework with onboard perception and conduct real-world experiments in both cluttered indoor and unstructured outdoor environments. The results from the physical systems further demonstrate the applicability of our method in challenging real-world environments.

    more » « less
  2. null (Ed.)
    Safety is a critical component in today's autonomous and robotic systems. Many modern controllers endowed with notions of guaranteed safety properties rely on accurate mathematical models of these nonlinear dynamical systems. However, model uncertainty is always a persistent challenge weakening theoretical guarantees and compromising safety. For safety-critical systems, this is an even bigger challenge. Typically, safety is ensured by constraining the system states within a safe constraint set defined a priori by relying on the model of the system. A popular approach is to use Control Barrier Functions (CBFs) that encode safety using a smooth function. However, CBFs fail in the presence of model uncertainties. Moreover, an inaccurate model can either lead to incorrect notions of safety or worse, incur system critical failures. Addressing these drawbacks, we present a novel safety formulation that leverages properties of CBFs and positive definite kernels to design Gaussian CBFs. The underlying kernels are updated online by learning the unmodeled dynamics using Gaussian Processes (GPs). While CBFs guarantee forward invariance, the hyperparameters estimated using GPs update the kernel online and thereby adjust the relative notion of safety. We demonstrate our proposed technique on a safety-critical quadrotor on SO(3) in the presence of model uncertainty in simulation. With the kernel update performed online, safety is preserved for the system. 
    more » « less
  3. Abstract

    Assessment of mitral valve (MV) function is important in many diagnostic, prognostic, and surgical planning applications for treatment of MV disease. Yet, to date, there are no accepted noninvasive methods for determination of MV leaflet deformation, which is a critical metric of MV function. In this study, we present a novel, completely noninvasive computational method to estimate MV leaflet in‐plane strains from clinical‐quality real‐time three‐dimensional echocardiography (rt‐3DE) images. The images were first segmented to produce meshed medial‐surface leaflet geometries of the open and closed states. To establish material point correspondence between the two states, an image‐based morphing pipeline was implemented within a finite element (FE) modeling framework in which MV closure was simulated by pressurizing the open‐state geometry, and local corrective loads were applied to enforce the actual MV closed shape. This resulted in a complete map of local systolic leaflet membrane strains, obtained from the final FE mesh configuration. To validate the method, we utilized an extant in vitro database of fiducially labeled MVs, imaged in conditions mimicking both the healthy and diseased states. Our method estimated local anisotropic in vivo strains with less than 10% error and proved to be robust to changes in boundary conditions similar to those observed in ischemic MV disease. Next, we applied our methodology to ovine MVs imaged in vivo with rt‐3DE and compared our results to previously published findings of in vivo MV strains in the same type of animal as measured using surgically sutured fiducial marker arrays. In regions encompassed by fiducial markers, we found no significant differences in circumferential(P = 0.240) or radial (P = 0.808) strain estimates between the marker‐based measurements and our novel noninvasive method. This method can thus be used for model validation as well as for studies of MV disease and repair.

    more » « less
  4. In this thesis we propose novel estimation techniques for localization and planning problems, which are key challenges in long-term autonomy. We take inspiration in our methods from non-parametric estimation and use tools such as kernel density estimation, non-linear least-squares optimization, binary masking, and random sampling. We show that these methods, by avoiding explicit parametric models, outperform existing methods that use them. Despite the seeming differences between localization and planning, we demonstrate in this thesis that the problems share core structural similarities. When real or simulation-sampled measurements are expensive, noisy, or high variance, non-parametric estimation techniques give higher-quality results in less time. We first address two localization problems. In order to permit localization with a set of ad hoc-placed radios, we propose an ultra-wideband (UWB) graph realization system to localize the radios. Our system achieves high accuracy and robustness by using kernel density estimation for measurement probability densities, by explicitly modeling antenna delays, and by optimizing this combination with a non-linear least squares formulation. Next, in order to then support robotic navigation, we present a flexible system for simultaneous localization and mapping (SLAM) that combines elements from both traditional dense metric SLAM and topological SLAM, using a binary "masking function" to focus attention. This masking function controls which lidar scans are available for loop closures. We provide several masking functions based on approximate topological class detectors. We then examine planning problems in the final chapter and in the appendix. In order to plan with uncertainty around multiple dynamic agents, we describe Monte-Carlo Policy-Tree Decision Making (MCPTDM), a framework for efficiently computing policies in partially-observable, stochastic, continuous problems. MCPTDM composes a sequence of simpler closed-loop policies and uses marginal action costs and particle repetition to improve cost estimates and sample efficiency by reducing variance. Finally, in the appendix we explore Learned Similarity Monte-Carlo Planning (LSMCP), where we seek to enhance the sample efficiency of partially observable Monte Carlo tree search-based planning by taking advantage of similarities in the final outcomes of similar states and actions. We train a multilayer perceptron to learn a similarity function which we then use to enhance value estimates in the planning. Collectively, we show in this thesis that non-parametric methods promote long-term autonomy by reducing error and increasing robustness across multiple domains. 
    more » « less
  5. This paper presents a novel architecture to attain a Unified Planner for Socially-aware Navigation (UP-SAN) and explains its need in Socially Assistive Robotics (SAR) applications. Our approach emphasizes interpersonal distance and how spatial communication can be used to build a unified planner for a human-robot collaborative environment. Socially-Aware Navigation (SAN) is vital to make humans feel comfortable and safe around robots, HRI studies have show that the importance of SAN transcendent safety and comfort. SAN plays a crucial role in perceived intelligence, sociability and social capacity of the robot thereby increasing the acceptance of the robots in public places. Human environments are very dynamic and pose serious social challenges to the robots indented for human interactions. For the robots to cope with the changing dynamics of a situation, there is a need to infer intent and detect changes in the interaction context. SAN has gained immense interest in the social robotics community; to the best of our knowledge, however, there is no planner that can adapt to different interaction contexts spontaneously after autonomously sensing that context. Most of the recent efforts involve social path planning for a single context. In this work, we propose a novel approach for a Unified Planner for SAN that can plan and execute trajectories that are human-friendly for an autonomously sensed interaction context. Our approach augments the navigation stack of Robot Operating System (ROS) utilizing machine learn- ing and optimization tools. We modified the ROS navigation stack using a machine learning-based context classifier and a PaCcET based local planner for us to achieve the goals of UP- SAN. We discuss our preliminary results and concrete plans on putting the pieces together in achieving UP-SAN. 
    more » « less