NAMOUnc: Navigation Among Movable Obstacles with Decision Making on Uncertainty Interval

TL;DR

NAMOUnc proposes an uncertainty-aware NAMO framework that treats observation, model, action, and blockage uncertainties as time-interval costs and optimizes between obstacle bypass and removal. It contributes four dedicated uncertainty-estimation modules, a GLR-based bypass-time predictor, a Beta-distributed SR model, and a Laplace-criterion decision mechanism to select safer, faster strategies under partial observability. Extensive simulations and real-robot experiments demonstrate improved reliability and efficiency over prior NAMO methods, including reduced planning time and fewer failures. The approach advances practical NAMO by enabling principled trade-offs between success rate and time, with potential extensions to energy efficiency and safety through broader objective optimization.

Abstract

Navigation among movable obstacles (NAMO) is a critical task in robotics, often challenged by real-world uncertainties such as observation noise, model approximations, action failures, and partial observability. Existing solutions frequently assume ideal conditions, leading to suboptimal or risky decisions. This paper introduces NAMOUnc, a novel framework designed to address these uncertainties by integrating them into the decision-making process. We first estimate them and compare the corresponding time cost intervals for removing and bypassing obstacles, optimizing both the success rate and time efficiency, ensuring safer and more efficient navigation. We validate our method through extensive simulations and real-world experiments, demonstrating significant improvements over existing NAMO frameworks. More details can be found in our website: https://kai-zhang-er.github.io/namo-uncertainty/

Figures (8)

• Figure 1: Primary sources of uncertainty in a NAMO task.The illustration highlights four key uncertainties encountered during task execution. The blue rectangle represents the MO while the green triangle with R denotes the robot. The red square labeled G indicates the goal. In subfigure (c), $X$ denotes the observation while $y$ and $\sigma$ represent the prediction result and the corresponding prediction uncertainty, respectively.
• Figure 2: Overview of the NAMO method pipeline. When being blocked by MOs during navigation, the robot estimates the bypass and removal cost to choose an efficient strategy to continue its task. The green cloud symbols represent the uncertainties associated with each module: (a) Observation uncertainty; (b) Model uncertainty; (c) Action uncertainty; (d) Blockage uncertainty caused by partial observability.
• Figure 3: Blocking case. The blue circle represents the MO in a corridor with width $W_i$. The green dash curve is the planned trajectory of the robot while the red dash line is the traversal line at waypoint $pt_i$
• Figure 4: Simulation environments. Two environments are used including a simple room and a complex warehouse. The blue regions are possible places for the MOs and the red region is the goal.
• Figure 5: Boxplot of the absolute error of prediction results for the three bypass time prediction methods. The box represents the interquartile range (IQR), with the lower and upper edges indicating the 25th (Q1) and 75th (Q3) percentiles, respectively. The notch and orange line in the box marks the median value of the absolute error. Whiskers extend to the smallest and largest values within 1.5 times the IQR from Q1 and Q3.