3260 papers • 126 benchmarks • 313 datasets
Trajectory planning for industrial robots consists of moving the tool center point from point A to point B while avoiding body collisions over time. Trajectory planning is sometimes referred to as motion planning and erroneously as path planning. Trajectory planning is distinct from path planning in that it is parametrized by time. Essentially trajectory planning encompasses path planning in addition to planning how to move based on velocity, time, and kinematics.
(Image credit: Papersgraph)
These leaderboards are used to track progress in trajectory-planning-5
Use these libraries to find trajectory-planning-5 models and implementations
No subtasks available.
This paper shows that a simple adaptation of this classical algorithm called revised prioritized planning is guaranteed to find collision-free trajectories for a well-defined class of practical problems, and proposes a new asynchronous decentralized adaptation of both classical and revised prioritization algorithm that can be used in multirobot systems without a central solver.
This work proposes a new end-to-end reinforcement learning approach to UAV-enabled data collection from Internet of Things (IoT) devices in an urban environment that enables the agent to make movement decisions for a variety of scenario parameters that balance the data collection goal with flight time efficiency and safety constraints.
This work proposes FASTER (Fast and Safe Trajectory Planner) to ensure safety without sacrificing speed, and obtains high-speed trajectories by enabling the local planner to optimize in both the free-known and unknown spaces.
A novel network named OFF-Net is proposed, which unifies Transformer architecture to aggregate local and global information, to meet the requirement of large receptive fields for freespace detection task and the cross-attention to dynamically fuse LiDAR and RGB image information for accurate off-road freespACE detection.
VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation, achieves state-of-the-art end-to-end planning performance on the nuScenes dataset, outperforming the previous best method by a large margin.
The global evolution of wireless technologies and intelligent sensing devices are transforming the realization of smart cities. Among the myriad of use cases, there is a need to support applications whereby low-resource IoT devices need to upload their sensor data to a remote control centre by target hard deadlines; otherwise, the data becomes outdated and loses its value, for example, in emergency or industrial control scenarios. In addition, the IoT devices can be either located in remote areas with limited wireless coverage or in dense areas with relatively low quality of service. This motivates the utilization of UAVs to offload traffic from existing wireless networks by collecting data from time-constrained IoT devices with performance guarantees. To this end, we jointly optimize the trajectory of a UAV and the radio resource allocation to maximize the number of served IoT devices, where each device has its own target data upload deadline. The formulated optimization problem is shown to be mixed integer non-convex and generally NP-hard. To solve it, we first propose the high-complexity branch, reduce and bound (BRB) algorithm to find the global optimal solution for relatively small scale scenarios. Then, we develop an effective sub-optimal algorithm based on successive convex approximation in order to obtain results for larger networks. Next, we propose an extension algorithm to further minimize the UAV’s flight distance for cases where the initial and final UAV locations are known a priori. We demonstrate the favourable characteristics of the algorithms via extensive simulations and analysis as a function of various system parameters, with benchmarking against two greedy algorithms based on distance and deadline metrics.
A new efficient algorithm which guarantees a solution for a class of multi-agent trajectory planning problems in obstacle-dense environments and generates safe, dynamically feasible trajectories without suffering from an erroneous optimization setup such as imposing infeasible collision constraints is presented.
This work builds upon existing parallelization strategies and extends them to continuous domains and examines the resulting parallelized continuous MCTS using a challenging cooperative multi-agent system trajectory planning task in the domain of automated vehicles.
The use of Reinforcement Learning for the robust design of low-thrust interplanetary trajectories in presence of severe disturbances, modeled alternatively as Gaussian additive process noise, observation noise, control actuation errors on thrust magnitude and direction, and possibly multiple missed thrust events is investigated.
Adding a benchmark result helps the community track progress.