Organizations: Eastern Institute of Technology, Ningbo, China · Tsinghua University, China · Department of Aeronautical and Aviation Engineering, Polytechnic University, Hong Kong
Mapless navigation in unknown and partially observable environments remains challenging for mobile robots, particularly when local minima prevent the robot from making progress toward its goal. Existing local navigation methods often lack an explicit mechanism for escaping such situations, while deep reinforcement learning (DRL) approaches typically learn recovery behaviors implicitly through reward design and policy optimization. In this work, we propose \textbf{LME} (Local-Minimum Escaper), a programmatic hierarchical framework that explicitly generates and reasons subgoals to guide robots out of local-minimum regions. LME operates solely on local observations and selects candidate subgoals using interpretable heuristic criteria that account for both surrounding obstacle geometry and candidate-location safety. A local planner then generates low-level motion commands toward the selected subgoal. This design enables LME to handle environments both with and without local minima within a unified framework, while remaining independent of the underlying local planner and requiring no additional training. Extensive experiments in simulated and real-world environments demonstrate that LME provides robust navigation performance and generalizes to challenging unseen scenarios. Furthermore, the generated subgoals can be used to guide different local planners, substantially improving their ability to escape local minima. Successful deployments on both differential-drive and quadruped robots further demonstrate the practical applicability and generality of the proposed framework.
Figures & tables
Fig. 1 : An illustration of the mapless navigation task. The blue lines represent the laser beams from the LiDAR. The red flag icon marks the final goal, while the several yellow stars represent the potential subgoals generated by LME.
Fig. 2 : Three separate figures.
Environment
Success rate ↑
Collision rate ↓
Timeout rate ↓
Env1
0.95±0.01
0.04 ±0.01
0.02 ±0.01
Env2
0.94±0.01
0.05 ±0.02
0.00 ±0.01
TABLE I : The performance of LME in ROS Stage.
Fig. 3 : Training map and testing map in ROS Stage.
Fig. 4 : A BARN scenario example.
Success rate ↑
Collision rate ↓
Timeout rate ↓
BARN Metric ↑
Use global planner
DWA
0.607±0.0094
0.253±0.0236
0.140±0.0141
0.3015±0.0049
No
DRL-DCLP
0.713±0.0094
0.077±0.0249
0.210±0.0163
0.3475±0.0052
No
S 3 -FISVFH
0.820±0.0216
0.113±0.0189
0.067±0.0047
0.3812±0.0074
No
E-Band
0.653
0.337
0.01
0.288
Yes
KUL+FM
0.860
0.02
0.12
0.388
Yes
DRL-VO
0.810
0.190
0
0.252
Yes
TABLE II : The performance of all methods on BARN environment.
Fig. 5 : Trajectories of several methods in BARN. The corresponding videos are provided in the supplementary file.
Fig. 6 : Visualization of features and the score S in BARN. To enhance contrast, extreme values are clipped to the 5th and 95th percentiles. Consistent with previous figures, the black line indicates the target direction, the green star denotes the selected subgoal, and the blue contour highlights a cluster of scan points when calculating amount .
Fig. 7 : Visualization of features and the score S in BARN.
Fig. 8 : Results of the ablation studies. The success rate is averaged over three independent runs.
Fig. 9 : Trajectories of different methods in Real1. The starting point marked as “S” and the goal point marked as “G”.
Fig. 10 : Trajectories of different methods in Real2.
Fig. 11 : Trajectories of different methods in Real3.
Fig. 12 : Trajectories of different methods in Real4.
Fig. 13 : Trajectories of DWA and LME-DWA.
Fig. 14 : Trajectories in dynamic obstacle scenarios.
A control framework is proposed for safe local navigation of mobile robots equipped with Ackermann steering in unmapped environments where a global goal is absent. Based on local obstacle detections, the safest heading angle is determined along the direction of the largest open space ahead of the vehicle. Guided by this direction, bounding lines are constructed on the left and right sides of the vehicle to achieve obstacle separation. These bounding lines are obtained by solving a convex quadratic optimization that maximizes vehicle-to-obstacle clearance. Optionally, conditions are imposed on the bounding lines to preserve parallelism and smooth abrupt changes from prior control steps. A feedback-linearizing controller is then used to regulate the vehicle's distance from one or both bounding lines, effectively enabling tracking of a local reference path that preserves safety through obstacle clearance maximization. Open-source code is included for the application of this control scheme. Experimental results demonstrate that the proposed method produces safer navigation paths with significantly shorter computation times, compared to some existing exploration-based planners.
Christian Schaible, Shahin Sirouspour
Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON L8S 4L8, Canada
Local navigation is one of the fundamental problems in robot navigation, and numerous approaches have been proposed over the years, including methods such as the Dynamic Window Approach, Model Predictive Control, and more recently, Control Barrier Functions and machine learning based techniques. While these methods perform well in simple environments, many of them rely on optimization or learning based procedures that can struggle in more complex scenarios. In contrast, this article proposes a more geometric algorithmic approach that enables a local navigation method with faster computation times and longer planning horizons. The proposed method is based on the computation of a sequence of circular regions from a local LiDAR scan that expand in the direction of the goal and capture free local navigable space. The proposed method was implemented in the ROS2 framework and evaluated in a simulated environment.
Scott Fredriksson, Akshit Saradagi, George Nikolakopoulos
Robotics and Artificial Intelligence Team Lule˚a University of Technology, Lule˚a, Sweden
Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to execute long-horizon instructions in unknown environments. Existing zero-shot VLN-CE systems typically maintain spatial states through geometric localization or coordinate-based representations. Recent geometry-constrained navigation removes depth and globally consistent coordinates, but maintaining persistent spatial awareness for place confirmation, progress verification, and recovery remains challenging. We present Navi-Agent, a zero-shot VLN-CE agent that constructs a coordinate-free spatial state from visual observations and executed motion histories. Navi-Agent organizes this state as a navigation topology, where nodes represent visual places and edges represent motion transitions. This representation enables observation-based approximate self-localization, task progress verification, and visual revisitation-based recovery. Navi-Agent performs closed-loop navigation by decomposing instructions into sub-goals, executing local visual navigation, and verifying visited places through the constructed spatial state. Experiments on zero-shot VLN-CE benchmark and real-world robot platforms show that Navi-Agent achieves state-of-the-art performance among geometry-constrained methods while remaining competitive with approaches relying on geometric localization.
Wenyuan Xie, Mengyang Hong, Yongzhong Wang +9
Shanghai Jiao Tong University · Southern University of Science and Technology · Xinjiang University of Finance and Economics +1