The humanoid robot Agile Justin is a platform for research in learning artificial intelligence (AI) for dextrous manipulation. Areas of application for the system are, in particular, household work and assisting astronauts in space.
The robot is continuously upgraded, its earliest predecessor was presented to the public in 2008.
• Whole-body control: 1 kHz rate (over all DOF)
• Head with 2 stereo cameras & RGB-D cameras
• Tactile skin with resolution: 1-5cm on body & 2mm on hands
• Computing: onboard: 4x Intel Xeon Quadcore
Agile Justin is one of the worldwide most advanced humanoid robots for mobile manipulation. It is equipped with sensorial and motor skills coming close to the human. DLR’s Autonomous Learning Lab uses Agile Justin as an ideal platform for research on modern learning artificial intelligence (AI) architectures, esp. generative AI and deep reinforcement learning (RL). The lab investigates learning as the core principle in perception, modeling and action in autonomous systems, which operate in complex and perpetually changing environments. Its most important upgrades compared to Rollin’Justin are the high resoultion tactile skin on the fingertips and the whole body, the wirelessly coupled large computing resources with a CPU und GPU cluster and the realtime distributed communication framework aRDx , developed specifically for the development of learning AI applications.
A selection of recent publications:
Agile Justin performing a precise joining task.
DLR (CC BY-NC-ND 3.0).
Agile Justin performing purely tactile dextrous in-hand manipulation. The strategy is learned from scratch in simulation using modern reinforcement learning methods.
Learned in-hand manipulation in detail. The object is rotated to any of the possible 90 deg orientation. Learning using a GPU takes only 1 hour.
Ballcatching: Catching flying balls is not easy. A tight interplay of fast perception, realtime whole-body motion planning and precise execution is needed.
Agile Justin performs the benchmark scenario “Building a Mars Habitat”. This demonstrates esp. the fast learning-based whole-body motion planning.
Agile Justin performs the benchmark scenario "Building a Mars Habitat". This demonstrates esp. the fast learning-based whole whole-body motion planning.