Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes

Chengyang Peng; Zhihao Zhang; Upama Pant; Yiming Wang; Keith A. Redmill; Ayonga Hereid

cs.ROOct 14, 2026

Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes

Authors: Chengyang Peng, Zhihao Zhang, Upama Pant, Yiming Wang, Keith A. Redmill, Ayonga Hereid

Organizations: Mechanical and Aerospace Engineering, The Ohio State University, Columbus, OH, USA. · Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA.

Abstract

Offline navigation demonstrations are multimodal, because one observation often allows several valid actions, such as passing an obstacle on either side. Behavior cloning averages these actions, potentially leading to unsafe routes. Multimodal policies must discover the alternatives from the data, but similar states can lead to different routes whose current actions overlap. In navigation, the alternatives have a geometric cause and can be computed from one observation. We propose a hierarchical neural-network policy that computes candidate modes from local geometry and learns from demonstrations which mode to follow and how. A high-level policy selects a mode using the goal and its previous choice among a set of candidate modes, and a low-level policy turns it into an action. In simulation, the policy succeeds in over 95% of seen and unseen test cases, compared with at most 43% and 20% for four offline learning baselines and 79% and 67% for a heuristic that uses the same modes without learning. The simulation-trained policy also transfers to a LimX Tron 1 bipedal robot.

Figures & tables

Panel of Figure 1 — Fig. 1 : (a). Averaging two feasible avoidance trajectories in behavior cloning produces a trajectory that collides directly with the obstacle. (b). Two obstacles (red and blue) partition the free space into three feasible forward directions. The tangent lines $\mathcal{H}_{1},\mathcal{H}_{2}$ and the observation-window edges (dashed) give three candidate modes $m_{1},m_{2},m_{3}$ .

Fig. 2 : Overview of the proposed framework. The observation $s_{t}$ is shown as the occupancy map $s_{occ}$ and the proprioception $s_{low}$ . The geometric module computes the candidate set $\mathcal{M}_{t}$ from $s_{occ}$ and the goal $g_{t}$ , and is not learned. Both policies are trained from demonstrations: the high-level policy $\pi_{H}$ selects a mode, conditioned on $s_{t}$ , $g_{t}$ , and the previous mode $m_{t-1}$ , and the low-level policy $\pi_{L}$ turns the selected mode $\hat{m}_{t}$ into a continuous action.

Fig. 3 : Examples of the four mode types, highlighted by orange circles. Type 0 lies between two obstacles. Types 1 and 2 pass one obstacle on the left and on the right. Type 3 points toward the goal.

Fig. 4 : An early branching case. Demonstrations that start from similar states follow distinct future paths (left), and their current actions form separate groups (right). For display, the paths show the next 20 steps of each demonstration, and colors mark the groups that our mode labeling method finds over these 20 steps.

Fig. 5 : An intermediate case. Demonstrations from similar states follow distinct future paths (left), but their current actions overlap and vary within each group (right). Colors as in Fig. 4 .

	Method	SR (%) $\uparrow$	CR (%) $\downarrow$	TR (%) $\downarrow$	Path R. $\downarrow$	Step R. $\downarrow$	Act. Jump (#/100) $\downarrow$	Comput. Time (ms) $\downarrow$
Seen	MLP-BC	42.8 $\pm$ 5.9	56.0 $\pm$ 6.0	1.2 $\pm$ 2.0	1.04	1.09	0	1.2
	DT	29.1 $\pm$ 6.8	70.9 $\pm$ 6.8	0	0.94	1.18	0.08 $\pm$ 0.07	3.0
	BeT	34.8 $\pm$ 1.8	65.0 $\pm$ 2.0	0.2 $\pm$ 0.3	0.97	1.04	1.50 $\pm$ 0.60	3.6
	DP	42.7 $\pm$ 3.2	55.2 $\pm$ 4.2	2.1 $\pm$ 1.7	1.12	1.18	3.38 $\pm$ 0.20	98.7
	Ours	96.5 $\pm$ 1.0	3.2 $\pm$ 1.0	0.3 $\pm$ 0.2	1.00	1.00	0.25 $\pm$ 0.02	2.9
Unseen	MLP-BC	20.0 $\pm$ 7.3	80.0 $\pm$ 7.3	0	0.88	0.91	0	1.4

TABLE I: Comparison with offline learning baselines. Path R. and Step R. are relative to Ours, on the cases that both methods complete. Mean

\pm

standard deviation over five training seeds (Sec. IV-A ).

	Method	SR (%) $\uparrow$	CR (%) $\downarrow$	TR (%) $\downarrow$	Path R. $\downarrow$	Step R. $\downarrow$	Act. Jump (#/100) $\downarrow$	Comput. Time (ms) $\downarrow$	Mode Sw. (#/100) $\downarrow$
Seen	w/o Auxi.	70.4 $\pm$ 12.4	25.8 $\pm$ 11.3	3.8 $\pm$ 2.2	0.95	0.94	0	2.6	6.05 $\pm$ 0.41
	w/o Hier.	25.8 $\pm$ 15.5	60.3 $\pm$ 4.7	13.8 $\pm$ 15.3	1.27	1.17	0	2.4	N/A
	Mode-act.-only	97.8 $\pm$ 0.7	0.2 $\pm$ 0.2	2.0 $\pm$ 0.6	1.09	1.10	0.65 $\pm$ 0.08	3.0	5.36 $\pm$ 0.09
	Heuristic	79.2	8.4	12.4	1.01	1.27	12.14	2.2	17.79
	Ours	96.5 $\pm$ 1.0	3.2 $\pm$ 1.0	0.3 $\pm$ 0.2	1.00	1.00	0.25 $\pm$ 0.02	2.9	5.53 $\pm$ 0.05
Unseen	w/o Auxi.	62.0 $\pm$ 22.0	30.7 $\pm$ 21.5	7.3 $\pm$ 3.9	0.91	0.90	0	3.3	7.41 $\pm$ 0.77

TABLE II: Comparison with the model variants. Metrics as in Table I . The Heuristic is not trained, so it has no

\pm

. w/o Hier. selects no mode, so it has no mode switches (N/A).

Panel of Figure 8 — Fig. 6 : Trajectories of the Heuristic and Ours in two test cases. (a) A seen case: the Heuristic collides with an obstacle ( $\times$ ), while Ours reaches the goal. (b) An unseen case: both reach the goal by different routes.

	Case (a)		Case (b)
	Heuristic	Ours	Heuristic	Ours
Outcome	Collision	Success	Success	Success
Steps	108 (F)	103	143	98
Path length (m)	5.3 (F)	6.9	5.9	5.7
Action jumps	30	0	40	1
Large turns	32	0	19	5

TABLE III: The seen case (a) and the unseen case (b) of Fig. 6 . Counts are totals over the trial. (F): failed trial.

Fig. 7 : Navigation on the LimX Tron 1 robot. (a) Laboratory with static obstacles. (b) Map built by the robot’s perception, with the path of the robot from start to goal. (c) Local occupancy maps at three stages of the run, with the candidate modes and the selected mode (circled); the markers in (b) show where each map was taken.

Fig. 8 : Deployments in three more indoor environments: (a) a public study area, (b) table avoidance and return, (c) a doorway from the laboratory into a corridor.

Robot Navigation

Robot navigation studies how robots perceive, localize, plan, and move safely toward goals in static or changing environments.

See all 549 papers

CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting
Oct 9, 2026Xianghui Wang, Xinming Zhang, Yiwei Qian +4Robot Navigation Cross-Embodiment Robot Learning
Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong · College of Information Science and Technology, Eastern Institute of Technology, Ningbo, China · School of Computer Science and Technology, University of Science and Technology of China, Hefei, China +2
NavOL: Navigation Policy with Online Imitation Learning
May 12, 2026Xiaofei Wei, Chun Gu, Li ZhangVisual Navigation Robot Navigation
School of Data Science, Fudan University · 2Shanghai Innovation Institute.
Multimodal embodiment-aware navigation transformer
Apr 21, 2026Louis Dezons, Quentin Picard, Rémi Marsal +2Off-Road Robot Navigation Robot Navigation
AMIAD Pˆole Recherche, Palaiseau, France · U2IS, ENSTA, Institut Polytechnique de Paris, Palaiseau, France

Oct 9, 2026J/K move · Enter open · S save

CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting

Xianghui Wang, Xinming Zhang, Yiwei Qian, Siwei Cheng+3

Department of Mechanical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong · College of Information Science and Technology, Eastern Institute of Technology, Ningbo, China · School of Computer Science and Technology, University of Science and Technology of China, Hefei, China+2

Robot Navigation Cross-Embodiment Robot Learning Robot Learning Robot Imitation Learning Data-Efficient Robot Learning

Open paper AskPDF arXiv

Learning-based methods have demonstrated strong performance in mapless robot navigation. However, a learned policy remains restricted to the embodiment on which it was trained. Many cross-embodiment navigation methods require time-consuming online training and can still underperform target-specific policies. In fact, demonstrations collected on a source embodiment already contain navigation experience that is potentially reusable for deriving a policy for each target embodiment, but the embodiment mismatch prevents these demonstrations from directly serving as valid supervision for the target. In this article, we present CeDR-Nav, a cross-embodiment demonstration recasting framework that trains a dedicated navigation policy for each target embodiment from existing source demonstrations without online data collection. Geometry-consistent scaling with per-demonstration validity assessment converts the source demonstrations into target training data, and a target-specific Gaussian mixture policy generates feasible avoidance maneuvers for each target embodiment. Extensive quantitative simulations and real-world deployments across multiple robot platforms demonstrate the effectiveness of CeDR-Nav, with an average success-rate gain of 13.8 percentage points over DRL-DCLP in cross-embodiment simulations and target-specific policy training completed within seconds.

Abstract

Robot Navigation

Explore similar work

CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting

NavOL: Navigation Policy with Online Imitation Learning

Multimodal embodiment-aware navigation transformer