---
title: [RO-MAN2026] Safe and Efficient NavigationConsidering Texting Pedestrians viaAttention-Aware Cost-map Tuning
tags:  #プレゼン資料  
author: [Shunya Tadano](https://docswell.com/user/shunyatadano)
site: [Docswell](https://www.docswell.com/)
thumbnail: https://bcdn.docswell.com/page/GE5MVPG2E4.jpg?width=480
description: [RO-MAN2026] Safe and Efficient NavigationConsidering Texting Pedestrians viaAttention-Aware Cost-map Tuning by Shunya Tadano
published: August 26, 26
canonical: https://docswell.com/s/shunyatadano/5GN699-2026-08-26-roman2026
---
# Page. 1

![Page Image](https://bcdn.docswell.com/page/GE5MVPG2E4.jpg)

Safe and Efficient Navigation
Considering Texting Pedestrians via
Attention-Aware Cost-map Tuning
Shunya Tadano, Yusuke Tamura, Ankit A. Ravankar, Yasuhisa Hirata


# Page. 2

![Page Image](https://bcdn.docswell.com/page/972936Y1JR.jpg)

Research Overview
Motivation Robots should consider pedestrian attention
Distracted
Attentive
⚫ Trajectory Prediction
⚫ Attention classification
⚫ Adaptive costmap tuning
⚫ Evaluation with 12 participants
across 252 trials
1


# Page. 3

![Page Image](https://bcdn.docswell.com/page/DJY419G47M.jpg)

Background
Social robot navigation in shared human environments
Safety to avoid collision
Legibility to make robot acceptable
Robots need to adapt to surrounding pedestrians
2


# Page. 4

![Page Image](https://bcdn.docswell.com/page/V7NY2LG6E8.jpg)

Background
Distracted pedestrians are hard for robots to handle
⚫ Smartphone use can change gait and slow
responses [Sajewicz+, 2023; Murakami+, 2021]
⚫ 12 - 45% of pedestrians distracted
[Simmons+, 2020]
Robots should understand not only pedestrian motion,
but also pedestrian attention
3


# Page. 5

![Page Image](https://bcdn.docswell.com/page/YJ9P14WR73.jpg)

Related Works
Existing approaches do not fully connect attention recognition to
navigation
Trajectory Prediction
Gaze / Head Pose
[Gupta+, 2018]
[Tu+, 2025]
Attention state ignored
Requires facial detail
Smartphone-Use Recognition
[Wu+, 2020]
Limited attention awareness
Attention recognition → Attention-aware cost-map tuning
4


# Page. 6

![Page Image](https://bcdn.docswell.com/page/GJ8D4QNGJD.jpg)

Objective
Make robot navigation responsive to pedestrian attention
This work proposes:
⚫ Attention classification using 3D
skeletal features
⚫ Adaptive costmap tuning based
on attention state
⚫ Evaluation with 12 participants
across 252 trials
Distracted
Attentive
5


# Page. 7

![Page Image](https://bcdn.docswell.com/page/LJLM6XPXER.jpg)

Method Overview
Data
Point
Cloud
Adaptive CostMap Generation
3D Pose
Estimation
Position
Image
Depth
Trajectory
Prediction
Future
Trajectory
Skelton
Point
Environment
Map
Attention
Classification
CostMap
Motion
Planning
Cost & Margin
Assignment
where to avoid
how cautiously to avoid
6


# Page. 8

![Page Image](https://bcdn.docswell.com/page/47MY5L437W.jpg)

Method: Trajectory Prediction
Trajectory
Prediction
Future
Trajectory
● Human Scene Transformer predicts future pedestrian trajectories
[Salzmann+, 2023]
● Input: past pedestrian pos & 3D skeleton (2 s / 6 steps)
● Output: future trajectory distribution (4 s / 12 steps )
7


# Page. 9

![Page Image](https://bcdn.docswell.com/page/P7R93KWRE9.jpg)

Method: Attention Classification
Attention
Classification
Cost & Margin
Assignment
● 3D skeletal features are extracted from RGB images [Bazarevsky+, 2020]
● A lightweight Random Forest enables real-time processing
8


# Page. 10

![Page Image](https://bcdn.docswell.com/page/PJXQ4LPY7X.jpg)

Classifier
Method: Skeletal Feature Extraction
Walking
3D pose est.
Phone
classification
⚫ 3D keypoints 𝒑 = {𝑝1 , … , 𝑝33 } MediaPipe BlazePose
⚫ Skeleton point Normalization with the hip (𝑝23 , 𝑝24 )
𝒑′𝒊 = 𝒑𝒊 − (𝒑𝟐𝟒 + 𝒑𝟐𝟒 ) / 2
9


# Page. 11

![Page Image](https://bcdn.docswell.com/page/3JK9ZLD4JD.jpg)

Attention Classification Results
● Classification accuracy: 95.1%
● Wrist and upper-body keypoints contributed most
● Consistent with characteristic smartphone-use postures
10


# Page. 12

![Page Image](https://bcdn.docswell.com/page/LE3WD3RDE5.jpg)

Method: Adaptive Cost-Map Tuning
Adaptive CostMap Generation
Environment
Map
CostMap
⚫ Add predicted pedestrian trajectories to the navigation cost map
[Lu+, 2014; Rösmann+, 2012]
⚫ The robot changes its avoidance behavior according to
pedestrian attention
11


# Page. 13

![Page Image](https://bcdn.docswell.com/page/8EDKP4Y27G.jpg)

Method: Attention-Aware Cost-Map Tuning
Trajectory predictions → map as navigation costs
Cost
Low
High
⚫ Traj. Prediction
⚫ Dynamic Obstacles
⚫ Static Obstacles
Attention Classification
⚫ Attentive: safety-margin radius = 0.3 m
⚫ Distracted: safety-margin radius = 0.5 m
12


# Page. 14

![Page Image](https://bcdn.docswell.com/page/V7PKNM6LJ8.jpg)

Experimental Setup
⚫ T-shaped indoor corridor
⚫ 12 participants, aged 22–28
⚫ 21 trials per participants
(7 trials × 3 methods)
Straight Scenario
Intersection Scenario
13


# Page. 15

![Page Image](https://bcdn.docswell.com/page/2JVVK936JQ.jpg)

Four Pedestrian Behaviors
Normal
Texting → Normal
Texting
Normal → Texting
14


# Page. 16

![Page Image](https://bcdn.docswell.com/page/5EGLQZ32JL.jpg)

Experimental Setup
Method
LiDAR-only
Prediction
Attention
✗
✗
⚫ Dynamic Obstacles
⚫ Static Obstacles
15


# Page. 17

![Page Image](https://bcdn.docswell.com/page/4JQYKL597P.jpg)

Experimental Setup
Method
Prediction
Attention
LiDAR-only
✗
✗
Traj. Prediction
✓
✗
⚫ Traj. Prediction
⚫ Dynamic Obstacles
⚫ Static Obstacles
16


# Page. 18

![Page Image](https://bcdn.docswell.com/page/K74WPDVRE1.jpg)

Experimental Setup
Method
Prediction
Attention
LiDAR-only
✗
✗
Traj. Prediction
✓
✗
Attention-Aware (Ours)
✓
✓
⚫ Traj. Prediction
⚫ Dynamic Obstacles
⚫ Static Obstacles
Attention Classification
⚫ Attentive: safety-margin radius = 0.3 m
⚫ Distracted: safety-margin radius = 0.5 m
17


# Page. 19

![Page Image](https://bcdn.docswell.com/page/LJ1Y9Z3VEG.jpg)

Quantitative Results: Motion Smoothness
Metric
LiDAR-only
Jerk RMS (m/s³) 
37.45±17.46
Traj. Prediction Attention-Aware (Ours)
11.01±8.62
11.42±9.19
● Prediction-based methods significantly reduced jerk RMS compared with the
LiDAR-only (p < 0.001)
● No significant difference in jerk RMS between Traj. Prediction and Ours
Trajectory prediction improves motion smoothness;
attention-aware tuning does not further reduce jerk.
18


# Page. 20

![Page Image](https://bcdn.docswell.com/page/GJWGQ9P372.jpg)

Quantitative Results
Metric
LiDAR-only Traj. Prediction Attention-Aware (Ours)
Min distance (m)
1.74±0.68
0.94±0.28
1.01±0.31
Max lateral. dev. (m) 
0.30±0.21
0.31±0.19
0.36±0.23
Travel time (s) 
16.8±2.1
17.0±1.9
16.9±2.0
⚫ Ours produced larger lateral deviations than Prediction
⚫ 8 of 12 participants noticed the behavioral difference while texting
(p = 0.050)
19


# Page. 21

![Page Image](https://bcdn.docswell.com/page/4EZLW9KG73.jpg)

Results: Subjective Evaluation
Item ()
LiDAR-only Traj. Prediction Attention-Aware (Ours)
Q1 Safety
4.6
4.69
5.07
Q2 Comfort
4.24
4.42
4.82
Q3 Smoothness
3.96
4.14
4.89
Q4 Naturalness
4.13
4.22
4.67
Q5 Predictability
3.69
4.01
4.48
Q6 Trust
4.49
4.64
4.96
Q7 Efficiency
4.38
4.57
4.93
Our method achieved the highest score at all metrics
20


# Page. 22

![Page Image](https://bcdn.docswell.com/page/Y76WGKQQ7V.jpg)

Results: Subjective Evaluation
* 𝑝 < .05
** 𝑝 > .01
Significant improvement in Smoothness / Predictability
21


# Page. 23

![Page Image](https://bcdn.docswell.com/page/G75MVPR274.jpg)

Takeaway
Motivation
⚫ Robots should also consider pedestrian attention
Method
⚫ 3D skeletal attention classification
with adaptive cost-map tuning
Key Finding
⚫ It improved perceived smoothness and
predictability without increasing travel time
Future Work
⚫ Temporal attention modeling
⚫ More complex scenarios
⚫ 360° perception
⚫ Broader participant population
22