Mastering dexterous robotic manipulation of deformable objects is vital for
overcoming the limitations of parallel grippers in real-world applications.
Current trajectory optimisation approaches often struggle to solve such tasks
due to the large search space and the limited task information available from a
cost function. In this work, we propose D-Cubed, a novel trajectory
optimisation method using a latent diffusion model (LDM) trained from a
task-agnostic play dataset to solve dexterous deformable object manipulation
tasks. D-Cubed learns a skill-latent space that encodes short-horizon actions
in the play dataset using a VAE and trains a LDM to compose the skill latents
into a skill trajectory, representing a long-horizon action trajectory in the
dataset. To optimise a trajectory for a target task, we introduce a novel
gradient-free guided sampling method that employs the Cross-Entropy method
within the reverse diffusion process. In particular, D-Cubed samples a small
number of noisy skill trajectories using the LDM for exploration and evaluates
the trajectories in simulation. Then, D-Cubed selects the trajectory with the
lowest cost for the subsequent reverse process. This effectively explores
promising solution areas and optimises the sampled trajectories towards a
target task throughout the reverse diffusion process. Through empirical
evaluation on a public benchmark of dexterous deformable object manipulation
tasks, we demonstrate that D-Cubed outperforms traditional trajectory
optimisation and competitive baseline approaches by a significant margin. We
further demonstrate that trajectories found by D-Cubed readily transfer to a
real-world LEAP hand on a folding task.

利用潜在扩散模型进行机器人灵巧可变形物体操控的轨迹优化，通过渐变自由引导采样方法和反扩散过程，发现并优化可行解，显著超越传统的轨迹优化和竞争基准方法。

D-Cubed: 灵巧可塑操作的潜在扩散轨迹优化

D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous  Deformable Manipulation

The complex dynamics of animal manoeuvrability in the wild is extremely
challenging to study. The cheetah ($\textit{Acinonyx jubatus}$) is a perfect
example: despite great interest in its unmatched speed and manoeuvrability,
obtaining complete whole-body motion data from these animals remains an
unsolved problem. This is especially difficult in wild cheetahs, where it is
essential that the methods used are remote and do not constrain the animal's
motion. In this work, we use data obtained from cheetahs in the wild to present
a trajectory optimisation approach for estimating the 3D kinematics and joint
torques of subjects remotely. We call this approach kinetic full trajectory
estimation (K-FTE). We validate the method on a dataset comprising synchronised
video and force plate data. We are able to reconstruct the 3D kinematics with
an average reprojection error of 17.69 pixels (62.94 $\%$ PCK using the
nose-to-eye(s) length segment as a threshold), while the estimates produce an
average root-mean-square error of 171.3 N ($\approx$ 17.16 $\%$ of peak force
during stride) for the estimated ground reaction force when compared against
the force plate data. While the joint torques cannot be directly validated
against ground truth data, as no such data is available for cheetahs, the
estimated torques agree with previous studies of quadrupeds in controlled
settings. These results will enable deeper insight into the study of animal
locomotion in a more natural environment for both biologists and roboticists.

使用野生猎豹的数据，提出一种追踪优化方法来估计远程主体的三维运动学和关节扭矩，结果对动物的运动学和机器人学的研究提供了更深入的见解。

猎豹中释放的狂野运动：无标记的猎豹三维运动学和力量估计

Wild Motion Unleashed: Markerless 3D Kinematics and Force Estimation in  Cheetahs

Motion planning can be cast as a trajectory optimisation problem where a cost
is minimised as a function of the trajectory being generated. In complex
environments with several obstacles and complicated geometry, this optimisation
problem is usually difficult to solve and prone to local minima. However,
recent advancements in computing hardware allow for parallel trajectory
optimisation where multiple solutions are obtained simultaneously, each
initialised from a different starting point. Unfortunately, without a strategy
preventing two solutions to collapse on each other, naive parallel optimisation
can suffer from mode collapse diminishing the efficiency of the approach and
the likelihood of finding a global solution. In this paper we leverage on
recent advances in the theory of rough paths to devise an algorithm for
parallel trajectory optimisation that promotes diversity over the range of
solutions, therefore avoiding mode collapses and achieving better global
properties. Our approach builds on path signatures and Hilbert space
representations of trajectories, and connects parallel variational inference
for trajectory estimation with diversity promoting kernels. We empirically
demonstrate that this strategy achieves lower average costs than competing
alternatives on a range of problems, from 2D navigation to robotic manipulators
operating in cluttered environments.

近期计算硬件的进展使得并行轨迹优化成为可能，为解决模式坍塌和寻找全局解提供了一种策略，该研究基于路径标记和 Hilbert 空间表示的轨迹，连接并行变分推断与多样性促进核技术。通过实验证明该策略在多个问题中均可获得比竞争方法更低的平均成本。