More Like this

1. LeTO: Learning Constrained Visuomotor Policy With Differentiable Trajectory Optimization

   https://doi.org/10.1109/TASE.2024.3486542  

   Xu, Zhengtong; She, Yu (March 2025, IEEE Transactions on Automation Science and Engineering)

   This paper introduces LeTO, a method for learning constrained visuomotor policy with differentiable trajectory optimization. Our approach integrates a differentiable optimization layer into the neural network. By formulating the optimization layer as a trajectory optimization problem, we enable the model to end-to-end generate actions in a safe and constraint-controlled fashion without extra modules. Our method allows for the introduction of constraint information during the training process, thereby balancing the training objectives of satisfying constraints, smoothing the trajectories, and minimizing errors with demonstrations. This “gray box” method marries optimization-based safety and interpretability with powerful representational abilities of neural networks. We quantitatively evaluate LeTO in simulation and in the real robot. The results demonstrate that LeTO performs well in both simulated and real-world tasks. In addition, it is capable of generating trajectories that are less uncertain, higher quality, and smoother compared to existing imitation learning methods. Therefore, it is shown that LeTO provides a practical example of how to achieve the integration of neural networks with trajectory optimization. We release our code at https://github.com/ZhengtongXu/LeTO. 

   more » « less
2. Fast Robot Motion Planning with Collision Avoidance and Temporal Optimization

   https://doi.org/10.1109/ICARCV.2018.8581194  

   Lin, Hsien-Chung; Liu, Changliu; Tomizuka, Masayoshi (November 2018, 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV))

   Considering the growing demand of real-time motion planning in robot applications, this paper proposes a fast robot motion planner (FRMP) to plan collision-free and time-optimal trajectories, which applies the convex feasible set algorithm (CFS) to solve both the trajectory planning problem and the temporal optimization problem. The performance of CFS in trajectory planning is compared to the sequential quadratic programming (SQP) in simulation, which shows a significant decrease in iteration numbers and computation time to converge a solution. The effectiveness of temporal optimization is shown on the operational time reduction in the experiment on FANUC LR Mate 200iD/7L. 

   more » « less
3. B-spline Parameterized Joint Optimization of Reconstruction and K-space Sampling Patterns (BJORK) for Accelerated 2D Acquisition

   Wang, G; Luo, T; Nielsen, J.F.; Fessler, J.A.; Noll, D.C. (January 2021, International Society Magnetic Resonance in Medicine)

   The proposed approach, BJORK, provides a robust and generalizable workflow to jointly optimize non-Cartesian sampling patters and a physics-informed reconstruction. Several approaches, including re-parameterization of trajectories, multi-level optimization, and non-Cartesian unrolled neural networks, are introduced to improve training effect and avoid sub-optimal local minima. The invivo experiments show that the networks and trajectories learned on simulation dataset are transferable to the real acquisition even with different parameter-weighted MRI contrasts and noise-levels, and demonstrate improved image quality compared with previous learning-based and model-based trajectory optimization methods. 

   more » « less
4. Motor cortex activity across movement speeds is predicted by network-level strategies for generating muscle activity

   https://doi.org/10.7554/eLife.67620  

   Saxena, Shreya; Russo, Abigail A; Cunningham, John; Churchland, Mark M (May 2022, eLife)

   Learned movements can be skillfully performed at different paces. What neural strategies produce this flexibility? Can they be predicted and understood by network modeling? We trained monkeys to perform a cycling task at different speeds, and trained artificial recurrent networks to generate the empirical muscle-activity patterns. Network solutions reflected the principle that smooth well-behaved dynamics require low trajectory tangling. Network solutions had a consistent form, which yielded quantitative and qualitative predictions. To evaluate predictions, we analyzed motor cortex activity recorded during the same task. Responses supported the hypothesis that the dominant neural signals reflect not muscle activity, but network-level strategies for generating muscle activity. Single-neuron responses were better accounted for by network activity than by muscle activity. Similarly, neural population trajectories shared their organization not with muscle trajectories, but with network solutions. Thus, cortical activity could be understood based on the need to generate muscle activity via dynamics that allow smooth, robust control over movement speed. 

   more » « less
5. Robust Trajectory Execution for Multi-robot Teams Using Distributed Real-time Replanning

   https://doi.org/10.1007/978-3-030-05816-6_12  

   Şenbaşlar, Baskın; Hönig, Wolfgang; Ayanian, Nora (October 2018, Distributed Autonomous Robotic Systems)

   Robust trajectory execution is an extension of cooperative collision avoidance that takes pre-planned trajectories directly into account. We propose an algorithm for robust trajectory execution that compensates for a variety of dynamic changes, including newly appearing obstacles, robots breaking down, imperfect motion execution, and external disturbances. Robots do not communicate with each other and only sense other robots’ positions and the obstacles around them. At the high-level we use a hybrid planning strategy employing both discrete planning and trajectory optimization with a dynamic receding horizon approach. The discrete planner helps to avoid local minima, adjusts the planning horizon, and provides good initial guesses for the optimization stage. Trajectory optimization uses a quadratic programming formulation, where all safety-critical parts are formulated as hard constraints. At the low-level, we use buffered Voronoi cells as a multi-robot collision avoidance strategy. Compared to ORCA, our approach supports higher-order dynamic limits and avoids deadlocks better. We demonstrate our approach in simulation and on physical robots, showing that it can operate in real time. 

   more » « less