The overall network architecture is shown in Figure 1. This work was done when the author was with Rutgers University. The overall network architecture is shown in Figure 1. We also apply the ReLU activation after its first and second layers. Empirical evaluations show that NHE exhibits admissibility and consistency.

The reconstruction of Configuration Space (CS) from a limited number of samples plays a vital role in expediting motion planning for random tree algorithms. Traditionally, the evaluation of CS reconstruction is performed through collision checking. However, employing the collision checker as an evaluation measure can be misleading. In particular, a collision checker may exhibit high accuracy even when only a subset of the original CS is reconstructed, limiting the motion planner's ability to find paths comparable to those in the original CS. Additionally, a significant challenge arises when dealing with high-dimensional CSs, as it becomes increasingly difficult, if not impossible, to perform qualitative evaluations when working in dimensions higher than three. In this paper, we introduce a novel approach for representing high-dimensional CSs of manipulator robots in a 2D format. Specifically, we leverage the kinematic chain of manipulator robots and the human ability to perceive colors based on hue. This allows us to construct a visualization comprising a series of pairs of 2D projections. We showcase the efficacy of our method in representing a 7-degree-of-freedom CS of a manipulator robot in a 2D projection. This representation provides qualitative insights into the joint boundaries of the robot and the collision state combinations. From a quantitative perspective, we show that the proposed representation not only captures accuracy but also furnishes additional information, enhancing our ability to compare two different high-dimensional CSs during the deployment phase, beyond what is usually offered by the collision checker. The source code is publicly available on our repository.

Real-time and efficient path planning is critical for all robotic systems. In particular, it is of greater importance for industrial robots since the overall planning and execution time directly impact the cycle time and automation economics in production lines. While the problem may not be complex in static environments, classical approaches are inefficient in high-dimensional environments in terms of planning time and optimality. Collision checking poses another challenge in obtaining a real-time solution for path planning in complex environments. To address these issues, we propose an end-to-end learning-based framework viz., Path Planning and Collision checking Network (PPCNet). The PPCNet generates the path by computing waypoints sequentially using two networks: the first network generates a waypoint, and the second one determines whether the waypoint is on a collision-free segment of the path. The end-to-end training process is based on imitation learning that uses data aggregation from the experience of an expert planner to train the two networks, simultaneously. We utilize two approaches for training a network that efficiently approximates the exact geometrical collision checking function. Finally, the PPCNet is evaluated in two different simulation environments and a practical implementation on a robotic arm for a bin-picking application. Compared to the state-of-the-art path planning methods, our results show significant improvement in performance by greatly reducing the planning time with comparable success rates and path lengths.

Collision-free motion generation in unknown environments is a core building block for robot manipulation. Generating such motions is challenging due to multiple objectives; not only should the solutions be optimal, the motion generator itself must be fast enough for real-time performance and reliable enough for practical deployment. A wide variety of methods have been proposed ranging from local controllers to global planners, often being combined to offset their shortcomings. We present an end-to-end neural model called Motion Policy Networks (M$\pi$Nets) to generate collision-free, smooth motion from just a single depth camera observation. M$\pi$Nets are trained on over 3 million motion planning problems in over 500,000 environments. Our experiments show that M$\pi$Nets are significantly faster than global planners while exhibiting the reactivity needed to deal with dynamic scenes. They are 46% better than prior neural planners and more robust than local control policies. Despite being only trained in simulation, M$\pi$Nets transfer well to the real robot with noisy partial point clouds. Code and data are publicly available at https://mpinets.github.io.

Tensegrity robots, composed of rigid rods and flexible cables, are difficult to accurately model and control given the presence of complex dynamics and high number of DoFs. Differentiable physics engines have been recently proposed as a data-driven approach for model identification of such complex robotic systems. These engines are often executed at a high-frequency to achieve accurate simulation. Ground truth trajectories for training differentiable engines, however, are not typically available at such high frequencies due to limitations of real-world sensors. The present work focuses on this frequency mismatch, which impacts the modeling accuracy. We proposed a recurrent structure for a differentiable physics engine of tensegrity robots, which can be trained effectively even with low-frequency trajectories. To train this new recurrent engine in a robust way, this work introduces relative to prior work: (i) a new implicit integration scheme, (ii) a progressive training pipeline, and (iii) a differentiable collision checker. A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data. Simulated experiments show that once the recurrent differentiable engine has been trained given the low-frequency trajectories from MuJoCo, it is able to match the behavior of MuJoCo's system. The criterion for success is whether a locomotion strategy learned using the differentiable engine can be transferred back to the ground-truth system and result in a similar motion. Notably, the amount of ground truth data needed to train the differentiable engine, such that the policy is transferable to the ground truth system, is 1% of the data needed to train the policy directly on the ground-truth system.