BOBjörn Olofsson

Björn Olofsson

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Björn Olofsson has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Towards Intent-Aware Human-Robot Teaming: A Platform for Search-and-Rescue Operations

    by Rohith Prem Maben, Ayesha Jena, Björn Olofsson, Stefan Reitmann, Jacek Malec, Rogier Woltjer, Elin Anna Topp

  • Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings

    by Theodor Westny, David Axelsson, Björn Olofsson, Erik Frisk

  • Robust Predictive Motion Planning by Learning Obstacle Uncertainty

    by Jian Zhou, Yulong Gao, Ola Johansson, Björn Olofsson, Erik Frisk

    Safe motion planning for robotic systems in dynamic environments is nontrivial in the presence of uncertain obstacles, where estimation of obstacle uncertainties is crucial in predicting future motions of dynamic obstacles. The worst case characterization gives a conservative uncertainty prediction and may result in infeasible motion planning for the ego robotic system. In this article, an efficient, robust, and safe motion-planning algorithm is developed by learning the obstacle uncertainties online. More specifically, the unknown yet intended control set of obstacles is efficiently computed by solving a linear programming (LP) problem. The learned control set is used to compute forward reachable sets (FRSs) of obstacles that are less conservative than the worst case prediction. Based on the forward prediction, a robust model predictive controller is designed to compute a safe reference trajectory for the ego robotic system that remains outside the reachable sets of obstacles over the prediction horizon. The method is applied to a car-like mobile robot in both simulations and hardware experiments to demonstrate its effectiveness.


  • Model-Based Predictive Impedance Variation for Obstacle Avoidance in Safe Human–Robot Collaboration

    by Julian M. Salt Ducaju, Björn Olofsson, Rolf Johansson

    Human–robot collaboration (HRC) in manufacturing environments requires that physical safety can be guaranteed. Control methods that implicitly regulate the interaction forces between a controlled robot and its environment, such as impedance control, are often used for safety in HRC. However, these methods could be complemented by restricting the robot operational space for additional safety guarantees. In this context, obstacle avoidance might benefit from considering a prediction of the controlled-robot motion and/or the behavior of the human collaborator. To this end, we proposed to include linearized Safety Control Barrier Functions (SCBFs) in a linear Model Predictive Control (MPC) strategy for robot impedance variation online. The convex optimization problem that was obtained from our proposal presented two advantages compared to nonlinear MPC alternatives. First, optimality was ensured in our method under linearity assumptions on human guidance and linearized robot dynamics, whereas a controller synthesized by nonlinear MPC strategies would depend on the fundamental characteristics of the problem. Second, our method enabled implementation at a faster control frequency, thus allowing a rapid adaptation to changes occurring in the robot environment. Finally, experimental validation was performed using a Franka Emika Panda robot in a human–robot collaborative scenario, and the stability of the method was shown using Lyapunov theory. Note to Practitioners —Modern-day industrial manufacturing environments are characterized by collaboration between human operators and robot manipulators. In this scenario, where humans and robots share workspace, physical safety is required. This research aims to improve safety in human–robot collaboration by proposing a novel robot control strategy. In our approach, the interaction forces between the controlled robot and its environment were regulated implicitly using impedance control, to allow, among other interactions, that an operator could manually guide the robot. Then, obstacle avoidance was included to modify the robot impedance behavior for restricting undesired collisions with, for example, the operator head, while ensuring stability of the method. Our main contribution is that the proposed formulation allows to consider a prediction of the robot motion and/or the operator behavior for robot obstacle avoidance. It was shown in experiments with a real robot that adding prediction capabilities reduced the risk of undesired collisions, while also decreasing the robot trajectory error. Moreover, the method could be implemented at a fast rate so that the robot could react rapidly to changes in its environment. Also, this implementation allowed to achieve a minimal variation with respect to the nominal impedance behavior of the robot. To conclude, this method is intended for scenarios where a robot is required to interact with its, possible restricted, environment: for example, a robot with a drill attached to its end-effector that is being guided to modify its trajectory, but where the operator should not be allowed to accidentally be harmed; or a robot performing a polishing task where a section of the polished object should remain unpolished. Therefore, using the proposed robot control strategy, a possible extension of this research would be to provide an improved prediction of the human operator intention depending on the desired robotic task and the role of the operator.


  • Open Access

    Uncertainty-Aware Decision-Making and Planning for Autonomous Forced Merging

    by Jian Zhou, Yulong Gao, Björn Olofsson, Erik Frisk

    In this paper, we develop an uncertainty-aware decision-making and motion-planning method for an autonomous ego vehicle in forced merging scenarios, considering the motion uncertainty of surrounding vehicles. The method dynamically captures the uncertainty of surrounding vehicles by online estimation of their acceleration bounds, enabling a reactive but rapid understanding of the uncertainty characteristics of the surrounding vehicles. By leveraging these estimated bounds, a non-conservative forward occupancy of surrounding vehicles is predicted over a horizon, which is incorporated in both the decision-making process and the motion-planning strategy, to enhance the resilience and safety of the planned reference trajectory. The method successfully fulfills the tasks in challenging forced merging scenarios, and the properties are illustrated by comparison with several alternative approaches.

  • Open Access

    Diffusion-Based Environment-Aware Trajectory Prediction

    by Theodor Westny, Björn Olofsson, Erik Frisk

    The ability to predict the future trajectories of traffic participants is crucial for the safe and efficient operation of autonomous vehicles. In this paper, a diffusion-based generative model for multi-agent trajectory prediction is proposed. The model is capable of capturing the complex interactions between traffic participants and the environment, accurately learning the multimodal nature of the data. The effectiveness of the approach is assessed on large-scale datasets of real-world traffic scenarios, showing that our model outperforms several well-established methods in terms of prediction accuracy. By the incorporation of differential motion constraints on the model output, we illustrate that our model is capable of generating a diverse set of realistic future trajectories. Through the use of an interaction-aware guidance signal, we further demonstrate that the model can be adapted to predict the behavior of less cooperative agents, emphasizing its practical applicability under uncertain traffic conditions.

  • Interaction-Aware Motion Planning for Autonomous Vehicles With Multi-Modal Obstacle Uncertainty Predictions

    by Jian Zhou, Björn Olofsson, Erik Frisk

    This paper proposes an interaction and safety-aware motion-planning method for an autonomous vehicle in uncertain multi-vehicle traffic environments. The method integrates the ability of the interaction-aware interacting multiple model Kalman filter (IAIMM-KF) to predict interactive multi-modal maneuvers of surrounding vehicles, and the advantage of model predictive control (MPC) in planning an optimal trajectory in uncertain dynamic environments. The multi-modal prediction uncertainties, containing both the maneuver and trajectory uncertainties of surrounding vehicles, are considered in computing the reference targets and designing the collision-avoidance constraints of MPC for resilient motion planning of the ego vehicle. The MPC achieves safety awareness by incorporating a tunable parameter to adjust the predicted obstacle occupancy in the design of the safety constraints, allowing the approach to achieve a trade-off between performance and robustness. Based on the prediction of the surrounding vehicles, an optimal reference trajectory of the ego vehicle is computed by MPC to follow the time-varying reference targets and avoid collisions with obstacles. The efficiency of the method is illustrated in challenging highway-driving simulation scenarios and a driving scenario from a recorded traffic dataset.


  • MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction With Neural ODEs

    by Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk

    Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of metrics.