This video presents a comprehensive autonomous framework for large-scale material handling tasks using four key components: an RL-based attack point planner that processes noisy soil grid heights to determine grasping points, an RL-based throwing controller that exploits passive pendulum dynamics for precise material release, an RRT* path planner that computes obstacle-aware trajectories with sufficient clearance margins, and an RL-based waypoint following controller. The framework demonstrates reliable performance in pile transfer tasks, matching human performance in scooped soil per cycle while achieving more consistent throws that result in more compact piles with reduced spread. For dump truck loading tasks, the system reduces machine rotation speed by only 24% compared to 41% reduction by human experts, achieving performance comparable to moderately experienced human operators while adapting to unseen, unstructured work sites.
Deep Dive
Prerequisite Knowledge
- No data available.
Where to go next
- No data available.
Deep Dive
Large scale robotic material handling: Learning, planning, and controlAdded:
In this work, we present a comprehensive framework for the autonomous execution of large-scale material handling tasks.
The transfer of bulk material piles is typically performed by heavy hydraulic manipulators known as material handlers.
Our framework features four main components to automate bulk material handling tasks, which are an RL-based waypoint following controller, an RL-based throwing controller, an RL-based attack point planner, and an RRT* based path planner.
We first evaluate our framework on the pile transfer task.
The RL-based attack point planner processes noisy soil grid heights to determine the next grasping point. After grasping, the unconstrained RL throwing policy throws the material at the designated target location. The cycle then repeats continuously.
Our framework demonstrates reliable performance over extended operation, successfully relocating all the soil from the original pile.
Our attack point planner matches human performance in scooped soil per cycle.
Compared to a human expert operator, our throwing controller achieves more consistent throws to the target location, resulting in a more compact pile with reduced spread and a higher peak. Our framework can adapt to unseen, unstructured work sites with a waypoint planner.
To evaluate this capability, we create a virtual obstacle in the form of a wall.
The RRT* planner computes a path before every transition that clears the obstacle with sufficient margin to account for the under-actuated tool.
The combination of precise throwing and obstacle-aware path planning enables our framework to address a more complex material handling task, dump truck loading.
To dampen tool oscillations before releasing the material, the expert operator reduces the machine's rotation speed by 41% and significantly slows down the arm movement.
On the other hand, our framework, designed for such scenarios, reduces the speed by only 24%, bringing the efficiency of our system much closer to the human operator's level. Overall, the framework achieves a performance level comparable to that of a moderately experienced human operator for the dump truck loading task.
Related Videos
Beyond Robotics | European Rover Challenge 2026
beyondrobotics
189 views•2026-06-01
Beatbot Sora70: JetPulse Technology and AI obstacle avoidance and navigation!
DroidModderX
26K views•2026-06-02
Tesla FSD 14.3.3 Hits Phoenix Streets - FIRST LOOK
anthonystesla
114 views•2026-05-29
Elon Musk Just Revealed Fremont Line for Optimus Gen 3 Mass Production
TheAINexusOfficial
180 views•2026-05-30
人機一体「零式人機 ver.2」 子ども企画【おもしろ発見!モビリティー】 #乗り物 #automobile #robot #shorts
KyodoNews
1K views•2026-05-28
China’s New Luna AI Robot Looks Shockingly Human...
NextGenHumanoids
850 views•2026-05-28
Reachy Mini: the $300 open source robot you can actually hack — Andres Marafioti, Hugging Face
aiDotEngineer
662 views•2026-05-29
柔軟指×AI画像処理食品の仕分け作業システム!#柔軟指 #ロボット #自動化 #製造業をもっと盛り上げたい
KiQ_Robotics_Corp.
113 views•2026-05-28











