As robots increasingly integrate into everyday environments, ensuring their safe navigation around humans becomes imperative. Efficient and safe motion planning requires robots to account for human behavior, particularly in constrained spaces such as grocery stores or care homes, where interactions with multiple individuals are common. Prior research has employed Bayesian frameworks to model human rationality based on navigational intent, enabling the prediction of probabilistic trajectories for planning purposes. In this work, we present a simple yet novel approach for confidence-aware prediction that treats future predictions as particles. This framework is highly parallelized and accelerated on an graphics processing unit (GPU). As a result, this enables longer-term predictions at a frequency of 125 Hz and can be easily extended for multi-human predictions. Compared to existing methods, our implementation supports finer prediction time steps, yielding more granular trajectory forecasts. This enhanced resolution allows motion planners to respond effectively to subtle changes in human behavior. We validate our approach through real-world experiments, demonstrating a robot safely navigating among multiple humans with diverse navigational goals. Our results highlight the methods potential for robust and efficient human-robot coexistence in dynamic environments.
Figures & tables
Fig. 1 : In the experiment, the humans are tasked to navigate in an 9.6×5.4 meter room as demonstrated in the left picture. The picture on the right shows an RVIZ display of the human predictions and their goals (red).
Prediction Steps T
Setting
2
4
6
8
10
CPU
0.130
0.642
1.242
1.865
2.493
CPU w/ JIT
0.050
0.097
0.139
0.189
0.229
GPU
2.826
2.943
3.022
3.192
3.253
GPU w/ JIT
0.007
0.007
0.007
0.007
0.008
Speed Up
x 18
x 95
x 175
x 257
x 300
TABLE I : Wall clock (in seconds) for different device settings across varying number of prediction steps T , and speed-ups of our method compared to CPU (without JIT), which represents a naive Python implementation of the particle-based approach. Note that such an approach would already be must faster than full Bayesian inference without the use of particles.
Fig. 2 : Evolution of Human Predictions and visualized MPPI trajectories over three snapshots of the experiment. The coloured visualizations indicate the future predicted occupancies. (a) A human reaches a goal. (b) As the human starts to walk towards another goal, the predictions change to be the mean of the two goals (red). As a result, the robot slightly quickly adjusts it’s trajectory. (c) The human decides to walk to the lower left goal. Hence, the robot’s plan largely remains the same.
This abstract addresses the incorporation of human motion prediction into proactive and dynamic human-aware motion planning, with the goal of enabling safe collaboration between humans and robots. A deep learning, graph-based model is used to forecast human motion and is integrated into a planning framework. This framework employs a static roadmap along with a time-variant A* algorithm to modify the trajectory of a UR5e manipulator. This method greatly improves human-robot interaction and enables proactive collision avoidance by combining precise motion forecasts with adaptive trajectory planning.
Elena Basei, Edoardo Lamon, Matteo Saveriano +2
Department of Information Engineering and Computer Science, Universit`a di Trento, Trento, Italy. · Interdepartmental Robotics Labs (IDRA), University of Trento, Trento, Italy · Department of Industrial Engineering, Universit`a di Trento, Trento, Italy.
This paper compares three human motion prediction methods - GMM-based clustering, TransFusion, and Graph-Mixer - evaluating their effectiveness in human-robot collaboration. These predictions are valuable for improving robot motion planning by anticipating human movements and enhancing safety and efficiency in dynamic environments.
Placido Falqueto, Elena Basei, Edoardo Lamon +4
Dept. of Information Engineering and Computer Science (DISI), University of Trento, Trento, Italy · Department of Industrial Engineering (DII), University of Trento, Trento, Italy
Safe and socially compliant navigation remains a fundamental challenge for autonomous robots operating in human-populated environments. Beyond collision avoidance, robots must anticipate human motion and respect personal space to ensure human comfort. Model Predictive Control (MPC) offers a robust alternative to classical and data-driven methods, although its effectiveness strongly depends on accurate human motion prediction and efficient computation. This paper introduces SFM-NMPC, a Social Force Model-based Non-linear Model Predictive Control framework that embeds human motion prediction directly within the optimization loop. By incorporating the Social Force Model into the dynamic model of surrounding agents, the controller jointly predicts the trajectories of humans and robots over the prediction horizon, thereby enabling socially-aware planning. A tailored set of social cost functions guides the optimization toward human-compliant behaviors. Despite the increased model complexity, the proposed formulation runs in real time at 20 Hz. Extensive simulated testing in crowded environments demonstrates that SFM-NMPC outperforms state-of-the-art baselines in social compliance metrics while maintaining efficient and smooth navigation. Visual trajectory analysis and an ablation study further highlight the contribution of the embedded SFM dynamics and social cost terms, confirming the effectiveness of the proposed approach for real-world social navigation.
Stefano Trepella, Andrea Ostuni, Mauro Martini +5
Department of Electronics and Telecommunications, Politecnico di Torino, 10129, Torino, Italy. · School of Engineering, Pablo de Olavide University, Crta. Utr-era km 1, Seville, Spain