Organizations: Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi 24, Torino, 10129, Torino, Italy. · Innovation Center, Intesa Sanpaolo, Corso Inghilterra 3, Torino, 10138, Torino, Italy.
Social navigation is essential for autonomous service robots operating in human environments, but progress remains constrained by the lack of extensive real-world benchmarks. This paper presents the Real Social Navigation Testbed (RESONATE), a reproducible benchmark for human-aware navigation based on a unified robotic platform, a shared ROS 2 software stack, precise trajectory ground truth, and structured social interaction scenarios. We evaluate eight controller configurations, combining classical and predictive local planners with different social modeling strategies, over eight representative scenarios with five repetitions each, yielding 320 physical experiments. The benchmark combines quantitative navigation and social metrics with participant-based qualitative assessments to jointly measure efficiency, safety, comfort, and perceived social behavior. Results reveal scenario-dependent trade-offs among the tested methods. The algorithms that stands out for their performance are the DWA with Gaussian social costmaps for its reliability, and the SFM-MPPI to provide the best balance between robustness, navigation efficiency, and social acceptance. Overall, RESONATE supports the robotics community with a real-world benchmark, reusable baselines, data, and testbed, and a consistent evaluation protocol for advancing socially aware navigation research.
Figures & tables
Figure 1: The hardware used including: Jackal ( 1a and 1b ), agent neck-worn tracking frame ( 1c ) and VICON cameras ( 1d ).
Figure 2: The schematics for the RESONATE benchmark. The three blocks of the RESONATE benchmark suite are the input data, the navigation stack, and the evaluation, divided into the online trajectory collection and offline filtering and evaluation. The survey is acquired separately.
Figure 3: The figure on the left, Fig. 3a , represents how the costmap is modified by the Gaussian Costmap layer plugin. On the right, Fig. 3b depicts the forces derived by the SFM, which will be employed to compute the Social Work.
Complete Name
Acronym
Brief Description
Navigation metrics
Success Rate
SR
Computed as the percentage of successful runs.
Path Length [ m ]
PL
Total length of the robot’s path in meters.
Heading Changes [ rad ]
CHC
Cumulative heading change during the complete trajectory in radians.
Time to Goal [ s ]
TTG
Time taken in seconds to reach the goal.
Social metrics
Table 1: Selected quantitative metrics
Complete Name
Acronym
Brief description
Safety
SA
The ability to avoid collision, near-collision, or intruding human personal space
Friendliness
FR
The compliance with expected social norms
Naturalness
NA
Degree of smoothness of the robot trajectory
Avoidance foresight
AF
The ability to predict a human’s trajectory in advance and respond to unexpected changes to keep safety distances
Table 2: Selected qualitative metrics
Name
Description
DWA
Only local obstacles detection
DWAGSC
Gaussian costmap around people
SFM-DWA
SFM-based social cost
MPPI
Only local obstacles detection
MPPIGSC
Gaussian costmap around people
SFM-MPPI
SFM-based social cost
Table 3: Algorithm description
Name
Difficulty
Description
S1 - Passing
Moderate
The robot traverses a hallway starting from the center, and one person moves in the opposite direction, keeping to the right-hand side.
S2 - Overtaking
Moderate
The robot traverses a hallway starting from the right-hand side, with a person starting ahead of it and going in the same direction.
S3 - Crossing 1
Moderate
The robot has to reach a goal in front of it while two people cross from the same side, with a slight delay (the second person starts crossing when the other has almost reached the goal).
S4 - Crossing 2
Moderate
This crossing variation is similar, but the second person is on the opposite side at the start.
S5 - Crossing 3
Hard
The robot traverses the room while three people cross in an X shape, two of them side-by-side.
S6 - Narrow turn
Hard
The robot has to turn to enter a passage while a person has to exit that same passage. The robot then has to reach the goal near another person that is walking around a fixed point.
Table 4: Selected scenarios
Figure 4: Examples of navigation in scenarios S1 - Passing and S2 - Overtaking, taken in the laboratory
Figure 5: Trajectories associated to a successful run for each of the eight scenarios
Figure 6: Proxemics metrics as percentage of time spent in social spaces for each scenario.
Figure 7: Overall human evaluation presented as bar plots, reporting the mean values and standard deviations for all scenarios. SFM-MPPI tends to rank at the higher end of human preference.
Scenario
Navigator
SR ( % ) ↑
PL ( m ) ↓
TTG ( s ) ↓
SWs↓
AMD ( m ) ↑
CHC ( rad ) ↓
S1 - Passing
DWA
100
3.91
10.99
1.49
1.87
1.09
DWAGSC
100
4.16
14.60
1.76
1.92
1.02
SFM-DWA
100
4.02
11.55
1.03
1.88
1.06
MPPI
100
4.08
9.19
1.39
2.24
1.25
MPPIGSC
100
4.22
10.22
1.55
1.93
3.20
SFM-MPPI
100
4.26
10.72
1.30
2.30
2.86
Table 5: RESONATE quantitative results for the algorithms described in Table 3 along the various scenarios. SR is computed over the five runs of each combination of algorithm and scenario; PL, TTG and CHC are the mean of the successful runs, while SWs and AMD are the mean of all five runs. Best results are highlighted while second best are underlined.
Scenario
Navigator
SA ↑
FR ↑
NA↑
AF ↑
Overall ↑
S1 - Passing
DWA
1.40
1.40
2.40
1.80
1.75
DWAGSC
2.40
2.00
2.40
2.20
2.25
SFM-DWA
2.80
2.20
3.20
2.80
2.75
MPPI
3.60
3.20
3.40
4.20
3.60
MPPIGSC
3.40
3.00
2.60
3.20
3.05
SFM-MPPI
4.00
3.80
3.40
4.20
3.85
Table 6: RESONATE qualitative results for the algorithms described in Table 3 along the various scenarios. The results are the mean of all rated runs, including the unsuccessful ones, for each combination of algorithm and scenario. Best results are highlighted while second best are underlined.
Figure 8: Cross-metrics analysis. The figure shows that some correlations between metrics can be observed, as is the example of the AMD showing a similar trend to the Safety metric. Fig. 8a shows the results for the Passing scenario, while Fig. 8b shows the result for the Crossing 1 scenario
Social robot navigation studies how robots move safely and comfortably around people while respecting human behavior, preferences, and shared-space norms.
This paper presents a joint effort towards the development of a data-driven Social Robot Navigation metric to facilitate benchmarking and policy optimization for ground robots. We provide the motivations for our approach and describe our proposal to format and store rated social navigation trajectory datasets. Following these guidelines, we compiled a first version of the proposed dataset with 4427 trajectories -- 182 real and 4245 simulated -- and presented it to human raters, yielding a total of 4402 rated trajectories after data quality assurance. Notably, we provide the first all-encompassing learned social robot navigation metric (SN26), along qualitative and quantitative results, including the test loss achieved, a comparison against hand-crafted metrics, and an ablation study. All data, software, and model weights are publicly available.
Pilar Bachiller-Burgos, Ulysses Bernardet, Luis V. Calderita +8
Universidad de Extremadura, Spain · Aston University, Birmingham, United Kingdom · Logical Robotics, United States of America +5
Building upon the foundations laid by our previous work, this paper introduces Arena 5.0, the fifth iteration of our framework for robotics social navigation development and benchmarking. Arena 5.0 provides three main contributions: 1) The complete integration of NVIDIA Isaac Gym, enabling photorealistic simulations and more efficient training. It seamlessly incorporates Isaac Gym into the Arena platform, allowing the use of existing modules such as randomized environment generation, evaluation tools, ROS2 support, and the integration of planners, robot models, and APIs within Isaac Gym. 2) A comprehensive benchmark of state-of-the-art social navigation strategies, evaluated on a diverse set of generated and customized worlds and scenarios of varying difficulty levels. These benchmarks provide a detailed assessment of navigation planners using a wide range of social navigation metrics. 3) Extensive scenario generation and task planning modules for improved and customizable generation of social navigation scenarios, such as emergency and rescue situations. The platform's performance was evaluated by generating the aforementioned benchmark and through a comprehensive user study, demonstrating significant improvements in usability and efficiency compared to previous versions. Arena 5.0 is open source and available at https://github.com/Arena-Rosnav.
Volodymyr Shcherbyna, Linh Kästner, Duc Anh Do +13
Technical University Berlin (TUB), Germany · National University of Singapore (NUS), Singapore · Technical University Munich (TUM), Germany
Language models (LMs) are increasingly applied to robotic navigation; however, existing benchmarks primarily emphasize navigation success rates while paying limited attention to social compliance. Moreover, relying on large-scale LMs can raise efficiency concerns, as their heavy computational overhead leads to slower response times and higher energy consumption, making them impractical for real-time deployment on resource-constrained robotic platforms. In this work, we evaluate the social compliance of GPT-4o and Claude in robotic navigation and propose E-SocialNav, an efficient LM designed for socially compliant navigation. Despite being trained on a relatively small dataset, E-SocialNav consistently outperforms zero-shot baselines in generating socially compliant behaviors. By employing a two-stage training pipeline consisting of supervised fine-tuning followed by direct preference optimization, E-SocialNav achieves strong performance in both text-level semantic similarity to human annotations and action accuracy. The source code is available at https://github.com/Dr-LingXiao/ESocialNav.
Ling Xiao, Daeun Song, Xuesu Xiao +1
Hokkaido University, Sapporo, Japan · George Mason University, Virginia, United States · The University of Tokyo, Tokyo, Japan